Upload via GUI (324 Dateien)
This commit is contained in:
@@ -0,0 +1,16 @@
|
|||||||
|
---
|
||||||
|
name: verify-and-stop
|
||||||
|
description: Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Verify and stop
|
||||||
|
|
||||||
|
Translate acceptance conditions into smallest sufficient proof set.
|
||||||
|
|
||||||
|
- Reuse still-current results with matching repository state.
|
||||||
|
- Run focused checks before wider gates.
|
||||||
|
- Distinguish pass, fail, unavailable, and blocked exactly.
|
||||||
|
- Do not edit product code unless verification request includes fixes.
|
||||||
|
- Do not add polish, cleanup, or unrelated tests after criteria pass.
|
||||||
|
|
||||||
|
Stop immediately when acceptance proof is complete. Report commands, results, and unresolved risk only.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Verify and Stop"
|
||||||
|
short_description: "Run relevant proof then stop cleanly"
|
||||||
|
default_prompt: "Use $verify-and-stop to prove acceptance criteria without adding scope."
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
{
|
||||||
|
"version": "0.0.1",
|
||||||
|
"configurations": [
|
||||||
|
{
|
||||||
|
"name": "aero-webseite",
|
||||||
|
"runtimeExecutable": "powershell",
|
||||||
|
"runtimeArgs": ["-NoProfile", "-Command", "Set-Location 'C:/Users/Viper/Desktop/Aero-Webseite'; npm run dev"],
|
||||||
|
"port": 3000
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
@@ -0,0 +1,67 @@
|
|||||||
|
# cavecrew
|
||||||
|
|
||||||
|
Decision guide. When to delegate to caveman subagents instead of doing the work inline.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Tells main thread when to spawn a caveman-style subagent. Compact return
|
||||||
|
contracts can reduce repeated prose when results return to main context, but
|
||||||
|
effect depends on task, agent, and delegation count. This skill publishes no
|
||||||
|
universal reduction rate.
|
||||||
|
|
||||||
|
Three subagents:
|
||||||
|
|
||||||
|
| Subagent | Job | Use when |
|
||||||
|
|----------|-----|----------|
|
||||||
|
| `cavecrew-investigator` | Locate code (read-only) | "Where is X defined / what calls Y / list uses of Z" |
|
||||||
|
| `cavecrew-builder` | Surgical edit, 1-2 files | Scope is obvious, ≤2 files. Refuses 3+ file scope. |
|
||||||
|
| `cavecrew-reviewer` | Diff/file review | One-line findings with severity emoji |
|
||||||
|
|
||||||
|
Use vanilla `Explore` or `Code Reviewer` when you want prose, architecture commentary, or rationale. Use main thread directly for one-line answers and 3+ file refactors.
|
||||||
|
|
||||||
|
This skill is a decision guide, not a slash command. It activates when the conversation mentions delegation.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
Triggers on phrases like "delegate to subagent", "use cavecrew", "spawn investigator", "save context", "compressed agent output".
|
||||||
|
|
||||||
|
## Example chaining
|
||||||
|
|
||||||
|
Locate → fix → verify (most common):
|
||||||
|
|
||||||
|
1. `cavecrew-investigator` returns site list (`path:line`, symbol, note)
|
||||||
|
2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`
|
||||||
|
3. `cavecrew-reviewer` audits the resulting diff
|
||||||
|
|
||||||
|
Parallel scout: spawn 2-3 `cavecrew-investigator` calls in one message with different angles (defs, callers, tests). Aggregate in main.
|
||||||
|
|
||||||
|
## Model overrides
|
||||||
|
|
||||||
|
By default, `cavecrew-reviewer` and `cavecrew-investigator` pin `model: haiku` in their frontmatter; `cavecrew-builder` has no `model:` line (uses the API session default). Set env vars in your shell before launching Claude Code to override per-agent:
|
||||||
|
|
||||||
|
| Env var | Agent |
|
||||||
|
|---|---|
|
||||||
|
| `CAVECREW_REVIEWER_MODEL` | `cavecrew-reviewer` |
|
||||||
|
| `CAVECREW_BUILDER_MODEL` | `cavecrew-builder` |
|
||||||
|
| `CAVECREW_INVESTIGATOR_MODEL` | `cavecrew-investigator` |
|
||||||
|
|
||||||
|
Example: run reviewer on sonnet and keep others on default.
|
||||||
|
|
||||||
|
```sh
|
||||||
|
export CAVECREW_REVIEWER_MODEL=sonnet
|
||||||
|
```
|
||||||
|
|
||||||
|
Use the same model name strings you'd use in any Claude Code agent frontmatter (e.g. `haiku`, `sonnet`, `opus`).
|
||||||
|
|
||||||
|
Overrides patch only `model:` line in installed agent frontmatter; prompt body
|
||||||
|
stays untouched and continues receiving upstream updates. Only plugin installs
|
||||||
|
have local agent files to patch. Empty variables do nothing. Patch persists until
|
||||||
|
plugin update or reinstall.
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md): full decision matrix and output contracts
|
||||||
|
- [`agents/cavecrew-investigator.md`](../../agents/cavecrew-investigator.md)
|
||||||
|
- [`agents/cavecrew-builder.md`](../../agents/cavecrew-builder.md)
|
||||||
|
- [`agents/cavecrew-reviewer.md`](../../agents/cavecrew-reviewer.md)
|
||||||
|
- [Caveman README](../../README.md): repo overview
|
||||||
@@ -0,0 +1,77 @@
|
|||||||
|
---
|
||||||
|
name: cavecrew
|
||||||
|
description: >
|
||||||
|
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder`
|
||||||
|
(1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline
|
||||||
|
or using `Explore`. Their output is compressed, so main context lasts longer.
|
||||||
|
---
|
||||||
|
|
||||||
|
Cavecrew = three subagent presets that answer in ultracave voice (tool runs: one status line in, one out; nothing between routine calls). Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
|
||||||
|
|
||||||
|
## When to use cavecrew vs alternatives
|
||||||
|
|
||||||
|
| Task | Use |
|
||||||
|
|---|---|
|
||||||
|
| "Where is X defined / what calls Y / list uses of Z" | `cavecrew-investigator` |
|
||||||
|
| Same but you also want suggestions/architecture commentary | `Explore` (vanilla) |
|
||||||
|
| Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` |
|
||||||
|
| New feature / 3+ files / cross-cutting refactor | Main thread, or `feature-dev:code-architect` if installed |
|
||||||
|
| Review diff, branch, or file for bugs | `cavecrew-reviewer` |
|
||||||
|
| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) if installed, else main thread |
|
||||||
|
| One-line answer you already know | Main thread, no subagent |
|
||||||
|
|
||||||
|
Rule of thumb: **if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.**
|
||||||
|
|
||||||
|
## Why this exists (the real win)
|
||||||
|
|
||||||
|
Subagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` comes back as a compressed `path:line` table instead. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.
|
||||||
|
|
||||||
|
## Output contracts
|
||||||
|
|
||||||
|
What main thread can rely on per agent:
|
||||||
|
|
||||||
|
**`cavecrew-investigator`**
|
||||||
|
```
|
||||||
|
<Header>:
|
||||||
|
- path:line — `symbol` — short note
|
||||||
|
totals: <counts>.
|
||||||
|
```
|
||||||
|
Or `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\d+`.
|
||||||
|
|
||||||
|
**`cavecrew-builder`**
|
||||||
|
```
|
||||||
|
<path:line-range> — <change ≤10 words>.
|
||||||
|
verified: <re-read OK | mismatch @ path:line>.
|
||||||
|
```
|
||||||
|
Or one of: `too-big.` / `needs-confirm.` / `ambiguous.` / `regressed.` (terminal first token).
|
||||||
|
|
||||||
|
**`cavecrew-reviewer`**
|
||||||
|
```
|
||||||
|
path:line: <emoji> <severity>: <problem>. <fix>.
|
||||||
|
totals: N🔴 N🟡 N🔵 N❓
|
||||||
|
```
|
||||||
|
Or `No issues.` Findings sorted file → line ascending.
|
||||||
|
|
||||||
|
## Chaining patterns
|
||||||
|
|
||||||
|
**Locate → fix → verify** (most common):
|
||||||
|
1. `cavecrew-investigator` returns site list.
|
||||||
|
2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`.
|
||||||
|
3. `cavecrew-reviewer` audits the diff.
|
||||||
|
|
||||||
|
**Parallel scout** (when investigation is broad):
|
||||||
|
Spawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.
|
||||||
|
|
||||||
|
**Single-shot edit** (when site is already known):
|
||||||
|
Skip investigator. Hand exact path:line to `cavecrew-builder` directly.
|
||||||
|
|
||||||
|
## What NOT to do
|
||||||
|
|
||||||
|
- Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.
|
||||||
|
- Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn.
|
||||||
|
- Don't ask `cavecrew-reviewer` for "general feedback" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that when installed.
|
||||||
|
- Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.
|
||||||
|
|
||||||
|
## Auto-clarity (inherited)
|
||||||
|
|
||||||
|
Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.
|
||||||
@@ -0,0 +1,44 @@
|
|||||||
|
# caveman-commit
|
||||||
|
|
||||||
|
Terse Conventional Commits. Why over what.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Generates commit messages in Conventional Commits format. Subject ≤50 chars, hard cap 72. Imperative mood. Body only when the *why* is non-obvious or there are breaking changes. No AI attribution, no "this commit does X", no emoji unless the project uses them. Body always required for breaking changes, security fixes, data migrations, and reverts — future debuggers need the context.
|
||||||
|
|
||||||
|
Outputs only the message. Does not stage, commit, or amend.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-commit
|
||||||
|
```
|
||||||
|
|
||||||
|
Also triggers on phrases like "write a commit", "commit message", "generate commit".
|
||||||
|
|
||||||
|
## Example output
|
||||||
|
|
||||||
|
Diff: new endpoint for user profile.
|
||||||
|
|
||||||
|
```
|
||||||
|
feat(api): add GET /users/:id/profile
|
||||||
|
|
||||||
|
Mobile client needs profile data without the full user payload
|
||||||
|
to reduce LTE bandwidth on cold-launch screens.
|
||||||
|
|
||||||
|
Closes #128
|
||||||
|
```
|
||||||
|
|
||||||
|
Diff: breaking API rename.
|
||||||
|
|
||||||
|
```
|
||||||
|
feat(api)!: rename /v1/orders to /v1/checkout
|
||||||
|
|
||||||
|
BREAKING CHANGE: clients on /v1/orders must migrate to /v1/checkout
|
||||||
|
before 2026-06-01. Old route returns 410 after that date.
|
||||||
|
```
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md) — full LLM-facing instructions
|
||||||
|
- [Caveman README](../../README.md) — repo overview
|
||||||
@@ -0,0 +1,63 @@
|
|||||||
|
---
|
||||||
|
name: caveman-commit
|
||||||
|
description: >
|
||||||
|
Write a Conventional Commits message compressed to intent only. Use for
|
||||||
|
"write a commit", "commit message", /commit or /caveman-commit.
|
||||||
|
---
|
||||||
|
|
||||||
|
Write commit messages terse and exact. Conventional Commits format. No fluff. Why over what.
|
||||||
|
|
||||||
|
## Rules
|
||||||
|
|
||||||
|
**Subject line:**
|
||||||
|
- `<type>(<scope>): <imperative summary>` — `<scope>` optional
|
||||||
|
- Types: `feat`, `fix`, `refactor`, `perf`, `docs`, `test`, `chore`, `build`, `ci`, `style`, `revert`
|
||||||
|
- Imperative mood: "add", "fix", "remove" — not "added", "adds", "adding"
|
||||||
|
- ≤50 chars when possible, hard cap 72
|
||||||
|
- No trailing period
|
||||||
|
- Match project convention for capitalization after the colon
|
||||||
|
|
||||||
|
**Body (only if needed):**
|
||||||
|
- Skip entirely when subject is self-explanatory
|
||||||
|
- Add body only for: non-obvious *why*, breaking changes, migration notes, linked issues
|
||||||
|
- Wrap at 72 chars
|
||||||
|
- Bullets `-` not `*`
|
||||||
|
- Reference issues/PRs at end: `Closes #42`, `Refs #17`
|
||||||
|
|
||||||
|
**What NEVER goes in:**
|
||||||
|
- "This commit does X", "I", "we", "now", "currently" — the diff says what
|
||||||
|
- "As requested by..." — use Co-authored-by trailer
|
||||||
|
- "Generated with Claude Code" or any AI attribution — unless the user's own rule requires an `Assisted-by`/AI-attribution trailer, then add it as a trailer
|
||||||
|
- Emoji (unless project convention requires)
|
||||||
|
- Restating the file name when scope already says it
|
||||||
|
|
||||||
|
## Examples
|
||||||
|
|
||||||
|
Diff: new endpoint for user profile with body explaining the why
|
||||||
|
- ❌ "feat: add a new endpoint to get user profile information from the database"
|
||||||
|
- ✅
|
||||||
|
```
|
||||||
|
feat(api): add GET /users/:id/profile
|
||||||
|
|
||||||
|
Mobile client needs profile data without the full user payload
|
||||||
|
to reduce LTE bandwidth on cold-launch screens.
|
||||||
|
|
||||||
|
Closes #128
|
||||||
|
```
|
||||||
|
|
||||||
|
Diff: breaking API change
|
||||||
|
- ✅
|
||||||
|
```
|
||||||
|
feat(api)!: rename /v1/orders to /v1/checkout
|
||||||
|
|
||||||
|
BREAKING CHANGE: clients on /v1/orders must migrate to /v1/checkout
|
||||||
|
before 2026-06-01. Old route returns 410 after that date.
|
||||||
|
```
|
||||||
|
|
||||||
|
## Auto-Clarity
|
||||||
|
|
||||||
|
Always include body for: breaking changes, security fixes, data migrations, anything reverting a prior commit. Never compress these into subject-only — future debuggers need the context.
|
||||||
|
|
||||||
|
## Boundaries
|
||||||
|
|
||||||
|
Only generates the commit message. Does not run `git commit`, does not stage files, does not amend. Output the message as a code block ready to paste. "stop caveman-commit" or "normal mode": revert to verbose commit style.
|
||||||
@@ -0,0 +1,218 @@
|
|||||||
|
<p align="center">
|
||||||
|
<img src="https://em-content.zobj.net/source/apple/391/rock_1faa8.png" width="80" />
|
||||||
|
</p>
|
||||||
|
|
||||||
|
<h1 align="center">caveman-compress</h1>
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<strong>shrink memory file. save token every session.</strong>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
A Claude Code skill that compresses project memory files (`CLAUDE.md`, todos,
|
||||||
|
preferences) into caveman format, reducing repeated input size.
|
||||||
|
|
||||||
|
Claude loads `CLAUDE.md` on every session start, so large files add repeated
|
||||||
|
input tokens. Caveman shortens supported natural-language files.
|
||||||
|
|
||||||
|
## What It Do
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-compress CLAUDE.md
|
||||||
|
```
|
||||||
|
|
||||||
|
```
|
||||||
|
CLAUDE.md ← compressed (Claude reads smaller file each session)
|
||||||
|
CLAUDE.original.md ← human-readable backup (you edit this)
|
||||||
|
```
|
||||||
|
|
||||||
|
Original remains in data directory rather than next to live file, so skill
|
||||||
|
auto-loaders do not read it twice. Path is
|
||||||
|
`$XDG_DATA_HOME/caveman-compress/backups/<parent-dir-name>/` on macOS and Linux,
|
||||||
|
or `%LOCALAPPDATA%\caveman-compress\backups\<parent-dir-name>\` on Windows. Edit
|
||||||
|
`.original.md` there, then run skill again to re-compress.
|
||||||
|
|
||||||
|
## Benchmarks
|
||||||
|
|
||||||
|
The five fixture pairs in [`tests/caveman-compress/`](../../tests/caveman-compress/),
|
||||||
|
counted with tiktoken o200k. Reproduce with
|
||||||
|
`uv run --with tiktoken python skills/caveman-compress/scripts/benchmark.py`.
|
||||||
|
|
||||||
|
| File | Original | Compressed | Saved |
|
||||||
|
|------|----------:|----------:|------:|
|
||||||
|
| `claude-md-preferences.md` | 827 | 421 | 49.1% |
|
||||||
|
| `claude-md-project.md` | 1628 | 1117 | 31.4% |
|
||||||
|
| `mixed-with-code.md` | 1432 | 1106 | 22.8% |
|
||||||
|
| `project-notes.md` | 1431 | 846 | 40.9% |
|
||||||
|
| `todo-list.md` | 880 | 648 | 26.4% |
|
||||||
|
| Total | 6198 | 4138 | 33.2% |
|
||||||
|
|
||||||
|
All fixture validations passed: headings, code blocks, URLs, and file paths were
|
||||||
|
preserved exactly.
|
||||||
|
|
||||||
|
## Before / After
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<tr>
|
||||||
|
<td width="50%">
|
||||||
|
|
||||||
|
### Original (827 tokens)
|
||||||
|
|
||||||
|
> "I strongly prefer TypeScript with strict mode enabled for all new code. Please don't use `any` type unless there's genuinely no way around it, and if you do, leave a comment explaining the reasoning. I find that taking the time to properly type things catches a lot of bugs before they ever make it to runtime."
|
||||||
|
|
||||||
|
</td>
|
||||||
|
<td width="50%">
|
||||||
|
|
||||||
|
### <img src="../../docs/assets/dancing-rock.svg" width="20" height="20" alt="rock"/> Caveman (421 tokens)
|
||||||
|
|
||||||
|
> "Prefer TypeScript strict mode always. No `any` unless unavoidable; comment why if used. Proper types catch bugs early."
|
||||||
|
|
||||||
|
</td>
|
||||||
|
</tr>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
This fixture produced 49.1% fewer counted tokens. Structural validation passed;
|
||||||
|
result does not prove semantic equivalence on other files or models.
|
||||||
|
|
||||||
|
## Security
|
||||||
|
|
||||||
|
`caveman-compress` is flagged as Snyk High Risk due to subprocess and file I/O
|
||||||
|
patterns detected by static analysis. See [SECURITY.md](./SECURITY.md) for why
|
||||||
|
these operations exist and how paths are constrained.
|
||||||
|
|
||||||
|
## Install
|
||||||
|
|
||||||
|
Compress is built into the `caveman` plugin. Install `caveman` once, then use `/caveman-compress`.
|
||||||
|
|
||||||
|
If you need local files, the compress skill lives at:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
skills/caveman-compress/
|
||||||
|
```
|
||||||
|
|
||||||
|
Requires Python 3.10 or newer.
|
||||||
|
|
||||||
|
### Provider / model
|
||||||
|
|
||||||
|
Default path uses Claude: `ANTHROPIC_API_KEY` + Anthropic SDK when set, else `claude --print`.
|
||||||
|
|
||||||
|
To use opencode instead (any model opencode can reach, free ones included):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
export CAVEMAN_COMPRESS_PROVIDER=opencode
|
||||||
|
export CAVEMAN_COMPRESS_MODEL=opencode/big-pickle # any id from `opencode models`
|
||||||
|
```
|
||||||
|
|
||||||
|
To use a local model (or any OpenAI-compatible server) instead:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
export CAVEMAN_COMPRESS_PROVIDER=openai-compat
|
||||||
|
export CAVEMAN_COMPRESS_MODEL=qwen3:8b # required
|
||||||
|
export CAVEMAN_COMPRESS_ENDPOINT=http://localhost:11434/v1 # default (Ollama)
|
||||||
|
# export CAVEMAN_COMPRESS_API_KEY=... # optional, sent as Bearer token
|
||||||
|
```
|
||||||
|
|
||||||
|
Common endpoints: Ollama `http://localhost:11434/v1`, LM Studio `http://localhost:1234/v1`, llama.cpp server `http://localhost:8080/v1`, vLLM `http://localhost:8000/v1`. Nothing leaves your machine with a local server. A non-local `http://` endpoint sends the file in plaintext; use `https://` for remote servers. Small local models get it wrong more often; when they do, validation fails and your file stays untouched.
|
||||||
|
|
||||||
|
`CAVEMAN_MODEL` is the fallback when `CAVEMAN_COMPRESS_MODEL` is unset. On the Claude path the model also applies to `claude --print`. The opencode path needs opencode 2.x (it uses `opencode run --standalone`).
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-compress <filepath>
|
||||||
|
```
|
||||||
|
|
||||||
|
Examples:
|
||||||
|
```
|
||||||
|
/caveman-compress CLAUDE.md
|
||||||
|
/caveman-compress docs/preferences.md
|
||||||
|
/caveman-compress todos.md
|
||||||
|
```
|
||||||
|
|
||||||
|
### What files work
|
||||||
|
|
||||||
|
| Type | Compress? |
|
||||||
|
|------|-----------|
|
||||||
|
| `.md`, `.mdc`, `.txt`, `.rst`, `.typ`, `.typst`, `.tex` | Yes |
|
||||||
|
| Extensionless natural language | Yes |
|
||||||
|
| `.py`, `.js`, `.ts`, `.json`, `.yaml` | ❌ Skip (code/config) |
|
||||||
|
| `*.original.md` | ❌ Skip (backup files) |
|
||||||
|
|
||||||
|
## How It Work
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-compress CLAUDE.md
|
||||||
|
↓
|
||||||
|
basic checks: file exists, under 500KB, not a sensitive filename
|
||||||
|
↓
|
||||||
|
acquire cross-session lock on the file (waits up to 15 min if another run holds it, then errors)
|
||||||
|
↓
|
||||||
|
detect file type (no tokens)
|
||||||
|
↓
|
||||||
|
configured provider compresses (tokens: one call)
|
||||||
|
↓
|
||||||
|
validate output (no tokens)
|
||||||
|
checks: headings, code blocks, URLs, file paths, bullets
|
||||||
|
↓
|
||||||
|
if errors: configured provider fixes cherry-picked issues only (tokens: targeted fix)
|
||||||
|
does NOT recompress; only patches broken parts
|
||||||
|
↓
|
||||||
|
retry up to 2 times
|
||||||
|
↓
|
||||||
|
write compressed → CLAUDE.md
|
||||||
|
write original → CLAUDE.original.md
|
||||||
|
```
|
||||||
|
|
||||||
|
Only two things use tokens: initial compression + targeted fix if validation fails. Everything else is local Python.
|
||||||
|
|
||||||
|
## What Is Preserved
|
||||||
|
|
||||||
|
Caveman compress natural language. It never touch:
|
||||||
|
|
||||||
|
- Code blocks (` ``` ` fenced or indented)
|
||||||
|
- Inline code (`` `backtick content` ``)
|
||||||
|
- URLs and links
|
||||||
|
- File paths (`/src/components/...`)
|
||||||
|
- Commands (`npm install`, `git commit`)
|
||||||
|
- Technical terms, library names, API names
|
||||||
|
- Headings (exact text preserved)
|
||||||
|
- Tables (structure preserved, cell text compressed)
|
||||||
|
- Dates, version numbers, numeric values
|
||||||
|
- Anything you wrap in `<!-- nocompress -->` ... `<!-- /nocompress -->`
|
||||||
|
|
||||||
|
Want a part left exactly as written (an `<example>` block, a prompt template)? Wrap it. Each tag go on its own line. Model never change what inside; it come back byte for byte. Model can still read it if first try need fixing, so not hiding place for secrets. Forget the closing tag and compress stop before touching file.
|
||||||
|
|
||||||
|
```markdown
|
||||||
|
<!-- nocompress -->
|
||||||
|
<example>
|
||||||
|
Reply in this exact format.
|
||||||
|
</example>
|
||||||
|
<!-- /nocompress -->
|
||||||
|
```
|
||||||
|
|
||||||
|
## Why This Matter
|
||||||
|
|
||||||
|
`CLAUDE.md` loads on every session start. A 1,000-token project memory file adds
|
||||||
|
1,000 input tokens each time project opens, or 100,000 across 100 sessions.
|
||||||
|
|
||||||
|
Caveman reduced counted tokens by 33.2% in total on the five listed fixtures
|
||||||
|
(22.8% to 49.1% per file). Validators confirmed headings, code blocks, URLs,
|
||||||
|
and file paths. They did not establish general semantic or task-quality
|
||||||
|
equivalence.
|
||||||
|
|
||||||
|
```
|
||||||
|
┌────────────────────────────────────────────┐
|
||||||
|
│ TOKEN SAVINGS, ALL FIVE ███ 33.2% │
|
||||||
|
│ FIXTURES IN TABLE 5 │
|
||||||
|
│ STRUCTURAL VALIDATION passed on all │
|
||||||
|
│ SETUP TIME █ 1x │
|
||||||
|
└────────────────────────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
## Part of Caveman
|
||||||
|
|
||||||
|
This skill is part of the [caveman](https://github.com/JuliusBrussee/caveman) toolkit.
|
||||||
|
|
||||||
|
- `caveman`: ask Claude to answer in shorter prose
|
||||||
|
- `caveman-compress`: shorten supported project-memory files with backups and validation
|
||||||
@@ -0,0 +1,41 @@
|
|||||||
|
# Security
|
||||||
|
|
||||||
|
## Snyk High Risk Rating
|
||||||
|
|
||||||
|
`caveman-compress` receives a Snyk High Risk rating due to static analysis heuristics. This document explains what the skill does and does not do.
|
||||||
|
|
||||||
|
### What triggers the rating
|
||||||
|
|
||||||
|
1. **subprocess usage**: The skill calls the `claude` CLI via `subprocess.run()` as a fallback when `ANTHROPIC_API_KEY` is not set. It can also call `opencode run` when `CAVEMAN_COMPRESS_PROVIDER=opencode`. Subprocess calls use fixed argument lists — no shell interpolation occurs. Claude receives user file content via stdin; opencode receives the generated prompt through a temporary `--file` attachment that is deleted after the call.
|
||||||
|
|
||||||
|
The file being compressed is untrusted input, and opencode 2.x lets its agents use every tool that is not explicitly denied: shell, file edits, web search and fetch, MCP tools from your opencode config, subagents. Compression needs none of them. Compress therefore runs `opencode run --standalone --agent caveman-compress` with `OPENCODE_CONFIG_CONTENT` denying every permission (`"*": "deny"`) both globally and for that agent, and never passes `--auto`. The dedicated agent matters because opencode applies a per-agent rule after the global one, so an `agent.build.permission` allow in your own config would otherwise re-enable a tool. `--standalone` matters because the shared opencode background service does not read the caller's environment, so the deny rule only binds a private server. Checked on opencode 2.0.22: the model is offered no tools and the prompt attachment is still read. Unlike the Claude path (`--strict-mcp-config`), compress does not switch off the MCP servers in your opencode config: their tools are denied, but opencode may still start them.
|
||||||
|
|
||||||
|
2. **File read/write**: The skill reads the file the user explicitly points it at, compresses it, and writes the result back to the same path. A `.original.md` backup is saved to an out-of-tree data dir (`$XDG_DATA_HOME/caveman-compress/backups/<parent-dir-name>/`, or `%LOCALAPPDATA%\caveman-compress\backups\<parent-dir-name>\` on Windows). The opencode provider writes a temporary prompt attachment in the OS temp directory and deletes it after the subprocess exits. Beyond the target file, that backup location, and the temporary attachment, no files are read or written.
|
||||||
|
|
||||||
|
### What the skill does NOT do
|
||||||
|
|
||||||
|
- Does not execute user file content as code
|
||||||
|
- Does not make network requests except through the configured LLM provider CLI, SDK, or (for `openai-compat`) the one configured HTTP endpoint
|
||||||
|
- Does not read unrelated files outside the path the user provides
|
||||||
|
- Does not use shell=True or string interpolation in subprocess calls
|
||||||
|
- Does not collect or transmit any data beyond the file being compressed
|
||||||
|
|
||||||
|
### Auth behavior
|
||||||
|
|
||||||
|
Default path uses Claude. If `ANTHROPIC_API_KEY` is set, the skill uses the Anthropic Python SDK directly (no subprocess). If not set, it falls back to the `claude` CLI, which uses the user's existing Claude desktop authentication.
|
||||||
|
|
||||||
|
Set `CAVEMAN_COMPRESS_PROVIDER=opencode` to use `opencode run` instead. Set `CAVEMAN_COMPRESS_MODEL=provider/model` for compress-specific model selection. `CAVEMAN_MODEL` is the fallback when `CAVEMAN_COMPRESS_MODEL` is unset.
|
||||||
|
|
||||||
|
Set `CAVEMAN_COMPRESS_PROVIDER=openai-compat` to POST the prompt with Python's standard-library `urllib` (no subprocess, no extra dependency) to `$CAVEMAN_COMPRESS_ENDPOINT/chat/completions`, default `http://localhost:11434/v1` (Ollama). Other local servers: LM Studio `http://localhost:1234/v1`, llama.cpp `http://localhost:8080/v1`, vLLM `http://localhost:8000/v1`. `CAVEMAN_COMPRESS_API_KEY`, if set, is sent as a Bearer token. A non-local `http://` endpoint sends the file and that key in plaintext; use `https://` for anything off the machine.
|
||||||
|
|
||||||
|
### File size limit
|
||||||
|
|
||||||
|
Files larger than 500KB are rejected before any API call is made.
|
||||||
|
|
||||||
|
### Snyk W007 ("insecure credential handling")
|
||||||
|
|
||||||
|
W007 fires on the rule that code blocks, commands, and exact error strings stay verbatim. See [Scanner warnings](../../SECURITY.md#scanner-warnings) in the repository SECURITY.md.
|
||||||
|
|
||||||
|
### Reporting a vulnerability
|
||||||
|
|
||||||
|
If you believe you've found a genuine security issue, please open a GitHub issue with the label `security`.
|
||||||
@@ -0,0 +1,109 @@
|
|||||||
|
---
|
||||||
|
name: caveman-compress
|
||||||
|
description: >
|
||||||
|
Compress a memory file such as CLAUDE.md or a todo list into caveman format
|
||||||
|
to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Caveman Compress
|
||||||
|
|
||||||
|
## Purpose
|
||||||
|
|
||||||
|
Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `<filename>.original.md`, but NOT beside the source file — it lives in an out-of-tree data dir (`$XDG_DATA_HOME/caveman-compress/backups/<parent-dir-name>/`, or `%LOCALAPPDATA%\caveman-compress\backups\<parent-dir-name>\` on Windows) so skill auto-loaders don't re-ingest it as a live file.
|
||||||
|
|
||||||
|
## Trigger
|
||||||
|
|
||||||
|
`/caveman-compress <filepath>` or when user asks to compress a memory file.
|
||||||
|
|
||||||
|
## Process
|
||||||
|
|
||||||
|
1. The compression scripts live in `scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `scripts/__main__.py` next to this SKILL.md.
|
||||||
|
|
||||||
|
2. From the directory containing this SKILL.md, run:
|
||||||
|
|
||||||
|
python3 -m scripts <absolute_filepath>
|
||||||
|
|
||||||
|
3. The CLI will:
|
||||||
|
- detect file type (no tokens)
|
||||||
|
- call Claude to compress
|
||||||
|
- validate output (no tokens)
|
||||||
|
- if errors: cherry-pick fix with Claude (targeted fixes only, no recompression)
|
||||||
|
- retry up to 2 times
|
||||||
|
- if still failing after 2 retries: report error to user, leave original file untouched
|
||||||
|
|
||||||
|
4. Return result to user
|
||||||
|
|
||||||
|
## Compression Rules
|
||||||
|
|
||||||
|
### Remove
|
||||||
|
- Articles: a, an, the
|
||||||
|
- Filler: just, really, basically, actually, simply, essentially, generally
|
||||||
|
- Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend"
|
||||||
|
- Hedging: "it might be worth", "you could consider", "it would be good to"
|
||||||
|
- Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because"
|
||||||
|
- Connective fluff: "however", "furthermore", "additionally", "in addition"
|
||||||
|
|
||||||
|
### Preserve EXACTLY (never modify)
|
||||||
|
- Code blocks (fenced ``` and indented)
|
||||||
|
- Inline code (`backtick content`)
|
||||||
|
- URLs and links (full URLs, markdown links)
|
||||||
|
- File paths (`/src/components/...`, `./config.yaml`)
|
||||||
|
- Commands (`npm install`, `git commit`, `docker build`)
|
||||||
|
- Technical terms (library names, API names, protocols, algorithms)
|
||||||
|
- Proper nouns (project names, people, companies)
|
||||||
|
- Dates, version numbers, numeric values
|
||||||
|
- Environment variables (`$HOME`, `NODE_ENV`)
|
||||||
|
|
||||||
|
### Preserve Structure
|
||||||
|
- All markdown headings (keep exact heading text, compress body below)
|
||||||
|
- Bullet point hierarchy (keep nesting level)
|
||||||
|
- Numbered lists (keep numbering)
|
||||||
|
- Tables (compress cell text, keep structure)
|
||||||
|
- Frontmatter/YAML headers in markdown files
|
||||||
|
|
||||||
|
### Compress
|
||||||
|
- Use short synonyms: "big" not "extensive", "fix" not "implement a solution for", "use" not "utilize"
|
||||||
|
- Fragments OK: "Run tests before commit" not "You should always run tests before committing"
|
||||||
|
- Drop "you should", "make sure to", "remember to" — just state the action
|
||||||
|
- Merge redundant bullets that say the same thing differently
|
||||||
|
- Keep one example where multiple examples show the same pattern
|
||||||
|
|
||||||
|
CRITICAL RULE:
|
||||||
|
Anything inside ``` ... ``` must be copied EXACTLY.
|
||||||
|
Do not:
|
||||||
|
- remove comments
|
||||||
|
- remove spacing
|
||||||
|
- reorder lines
|
||||||
|
- shorten commands
|
||||||
|
- simplify anything
|
||||||
|
|
||||||
|
Inline code (`...`) must be preserved EXACTLY.
|
||||||
|
Do not modify anything inside backticks.
|
||||||
|
|
||||||
|
If file contains code blocks:
|
||||||
|
- Treat code blocks as read-only regions
|
||||||
|
- Only compress text outside them
|
||||||
|
- Do not merge sections around code
|
||||||
|
|
||||||
|
## Pattern
|
||||||
|
|
||||||
|
Original:
|
||||||
|
> You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.
|
||||||
|
|
||||||
|
Compressed:
|
||||||
|
> Run tests before push to main. Catch bugs early, prevent broken prod deploys.
|
||||||
|
|
||||||
|
Original:
|
||||||
|
> The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.
|
||||||
|
|
||||||
|
Compressed:
|
||||||
|
> Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.
|
||||||
|
|
||||||
|
## Boundaries
|
||||||
|
|
||||||
|
- ONLY compress natural language files (.md, .txt, .typ, .typst, .tex, extensionless)
|
||||||
|
- NEVER modify: .py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh
|
||||||
|
- If file has mixed content (prose + code), compress ONLY the prose sections
|
||||||
|
- If unsure whether something is code or prose, leave it unchanged
|
||||||
|
- Original file is backed up as FILE.original.md before overwriting — in the out-of-tree backup data dir (see Purpose), not beside the source file
|
||||||
|
- Never compress FILE.original.md (skip it)
|
||||||
@@ -0,0 +1,9 @@
|
|||||||
|
"""Caveman compress scripts.
|
||||||
|
|
||||||
|
This package provides tools to compress natural language markdown files
|
||||||
|
into caveman format to save input tokens.
|
||||||
|
"""
|
||||||
|
|
||||||
|
__all__ = ["cli", "compress", "detect", "validate"]
|
||||||
|
|
||||||
|
__version__ = "1.0.0"
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
from .cli import main
|
||||||
|
|
||||||
|
main()
|
||||||
@@ -0,0 +1,80 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
from pathlib import Path
|
||||||
|
import sys
|
||||||
|
|
||||||
|
# Support both direct execution and module import
|
||||||
|
try:
|
||||||
|
from .validate import validate
|
||||||
|
except ImportError:
|
||||||
|
sys.path.insert(0, str(Path(__file__).parent))
|
||||||
|
from validate import validate
|
||||||
|
|
||||||
|
try:
|
||||||
|
import tiktoken
|
||||||
|
_enc = tiktoken.get_encoding("o200k_base")
|
||||||
|
except ImportError:
|
||||||
|
_enc = None
|
||||||
|
|
||||||
|
|
||||||
|
def count_tokens(text):
|
||||||
|
if _enc is None:
|
||||||
|
return len(text.split()) # fallback: word count
|
||||||
|
return len(_enc.encode(text))
|
||||||
|
|
||||||
|
|
||||||
|
def benchmark_pair(orig_path: Path, comp_path: Path):
|
||||||
|
orig_text = orig_path.read_text(encoding="utf-8", errors="ignore")
|
||||||
|
comp_text = comp_path.read_text(encoding="utf-8", errors="ignore")
|
||||||
|
|
||||||
|
orig_tokens = count_tokens(orig_text)
|
||||||
|
comp_tokens = count_tokens(comp_text)
|
||||||
|
saved = 100 * (orig_tokens - comp_tokens) / orig_tokens if orig_tokens > 0 else 0.0
|
||||||
|
result = validate(orig_path, comp_path)
|
||||||
|
|
||||||
|
return (comp_path.name, orig_tokens, comp_tokens, saved, result.is_valid)
|
||||||
|
|
||||||
|
|
||||||
|
def print_table(rows):
|
||||||
|
print("\n| File | Original | Compressed | Saved % | Valid |")
|
||||||
|
print("|------|----------|------------|---------|-------|")
|
||||||
|
for r in rows:
|
||||||
|
print(f"| {r[0]} | {r[1]} | {r[2]} | {r[3]:.1f}% | {'✅' if r[4] else '❌'} |")
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
# Direct file pair: python3 benchmark.py original.md compressed.md
|
||||||
|
if len(sys.argv) == 3:
|
||||||
|
orig = Path(sys.argv[1]).resolve()
|
||||||
|
comp = Path(sys.argv[2]).resolve()
|
||||||
|
if not orig.exists():
|
||||||
|
print(f"❌ Not found: {orig}")
|
||||||
|
sys.exit(1)
|
||||||
|
if not comp.exists():
|
||||||
|
print(f"❌ Not found: {comp}")
|
||||||
|
sys.exit(1)
|
||||||
|
print_table([benchmark_pair(orig, comp)])
|
||||||
|
return
|
||||||
|
|
||||||
|
# Glob mode: repo_root/tests/caveman-compress/
|
||||||
|
# __file__ lives at <repo_root>/skills/caveman-compress/scripts/benchmark.py
|
||||||
|
# Walk up four dirs: scripts → caveman-compress → skills → repo_root.
|
||||||
|
tests_dir = Path(__file__).resolve().parents[3] / "tests" / "caveman-compress"
|
||||||
|
if not tests_dir.exists():
|
||||||
|
print(f"❌ Tests dir not found: {tests_dir}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
rows = []
|
||||||
|
for orig in sorted(tests_dir.glob("*.original.md")):
|
||||||
|
comp = orig.with_name(orig.stem.removesuffix(".original") + ".md")
|
||||||
|
if comp.exists():
|
||||||
|
rows.append(benchmark_pair(orig, comp))
|
||||||
|
|
||||||
|
if not rows:
|
||||||
|
print("No compressed file pairs found.")
|
||||||
|
return
|
||||||
|
|
||||||
|
print_table(rows)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
@@ -0,0 +1,86 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""
|
||||||
|
Caveman Compress CLI
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
caveman <filepath>
|
||||||
|
"""
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import sys
|
||||||
|
|
||||||
|
# Force UTF-8 on stdout/stderr before any code can print. Windows consoles
|
||||||
|
# default to cp1252 and crash on the ❌ glyphs in error/validation branches,
|
||||||
|
# masking the real error and leaving the user with a half-compressed file.
|
||||||
|
for _stream in (sys.stdout, sys.stderr):
|
||||||
|
reconfigure = getattr(_stream, "reconfigure", None)
|
||||||
|
if callable(reconfigure):
|
||||||
|
try:
|
||||||
|
reconfigure(encoding="utf-8", errors="replace")
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# Direct script execution has no package context. Resolve imports relative to
|
||||||
|
# this installed skill, independent of the caller's working directory.
|
||||||
|
if __package__ in (None, ""):
|
||||||
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||||
|
__package__ = "scripts"
|
||||||
|
|
||||||
|
from .compress import backup_dir_for, compress_file
|
||||||
|
from .detect import detect_file_type, should_compress
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
parser = argparse.ArgumentParser(description="Compress a natural-language file with validation and an original backup.")
|
||||||
|
parser.add_argument("filepath", type=Path, help="path to the file to compress")
|
||||||
|
filepath = parser.parse_args().filepath
|
||||||
|
|
||||||
|
# Check file exists
|
||||||
|
if not filepath.exists():
|
||||||
|
print(f"❌ File not found: {filepath}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
if not filepath.is_file():
|
||||||
|
print(f"❌ Not a file: {filepath}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
filepath = filepath.resolve()
|
||||||
|
|
||||||
|
# Detect file type
|
||||||
|
file_type = detect_file_type(filepath)
|
||||||
|
|
||||||
|
print(f"Detected: {file_type}")
|
||||||
|
|
||||||
|
# Check if compressible
|
||||||
|
if not should_compress(filepath):
|
||||||
|
print("Skipping: file is not natural language (code/config)")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
print("Starting caveman compression...\n")
|
||||||
|
|
||||||
|
try:
|
||||||
|
success = compress_file(filepath)
|
||||||
|
|
||||||
|
if success:
|
||||||
|
print("\nCompression completed successfully")
|
||||||
|
backup_path = backup_dir_for(filepath) / (filepath.stem + ".original.md")
|
||||||
|
print(f"Compressed: {filepath}")
|
||||||
|
print(f"Original: {backup_path}")
|
||||||
|
sys.exit(0)
|
||||||
|
else:
|
||||||
|
print("\n❌ Compression failed after retries")
|
||||||
|
sys.exit(2)
|
||||||
|
|
||||||
|
except KeyboardInterrupt:
|
||||||
|
print("\nInterrupted by user")
|
||||||
|
sys.exit(130)
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
print(f"\n❌ Error: {e}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,144 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Detect whether a file is natural language (compressible) or code/config (skip)."""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import re
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# Extensions that are natural language and compressible. `.mdc` is a Cursor
|
||||||
|
# rule: prose with YAML frontmatter, the same shape as a SKILL.md, and the
|
||||||
|
# format caveman's own `--with-init` writes to `.cursor/rules/caveman.mdc`.
|
||||||
|
# Content sniffing below runs only for EXTENSIONLESS files, so an extension
|
||||||
|
# that is on neither list falls through to `unknown` and is never compressed.
|
||||||
|
COMPRESSIBLE_EXTENSIONS = {".md", ".mdc", ".txt", ".markdown", ".rst", ".typ", ".typst", ".tex"}
|
||||||
|
|
||||||
|
# Extensions that are code/config and should be skipped
|
||||||
|
SKIP_EXTENSIONS = {
|
||||||
|
".py", ".js", ".ts", ".tsx", ".jsx", ".json", ".yaml", ".yml",
|
||||||
|
".toml", ".env", ".lock", ".css", ".scss", ".html", ".xml",
|
||||||
|
".sql", ".sh", ".bash", ".zsh", ".go", ".rs", ".java", ".c",
|
||||||
|
".cpp", ".h", ".hpp", ".rb", ".php", ".swift", ".kt", ".lua",
|
||||||
|
".dockerfile", ".makefile", ".csv", ".ini", ".cfg",
|
||||||
|
}
|
||||||
|
|
||||||
|
# Well-known build/config files that carry no (or a misleading) extension —
|
||||||
|
# `Dockerfile` has no suffix so `.dockerfile` above never matches it, and
|
||||||
|
# `CMakeLists.txt` would ride the compressible `.txt` rule. Checked by
|
||||||
|
# basename before any extension rule.
|
||||||
|
KNOWN_CODE_FILENAMES = {
|
||||||
|
"dockerfile", "containerfile", "makefile", "gnumakefile", "jenkinsfile",
|
||||||
|
"vagrantfile", "rakefile", "gemfile", "justfile", "procfile", "brewfile",
|
||||||
|
"earthfile", "fastfile", "podfile",
|
||||||
|
"cmakelists.txt",
|
||||||
|
}
|
||||||
|
|
||||||
|
# Patterns that indicate a line is code
|
||||||
|
CODE_PATTERNS = [
|
||||||
|
re.compile(r"^\s*(import |from .+ import |require\(|const |let |var )"),
|
||||||
|
re.compile(r"^\s*(def |class |function |async function |export )"),
|
||||||
|
re.compile(r"^\s*(if\s*\(|for\s*\(|while\s*\(|switch\s*\(|try\s*\{)"),
|
||||||
|
re.compile(r"^\s*[\}\]\);]+\s*$"), # closing braces/brackets
|
||||||
|
re.compile(r"^\s*@\w+"), # decorators/annotations
|
||||||
|
re.compile(r'^\s*"[^"]+"\s*:\s*'), # JSON-like key-value
|
||||||
|
re.compile(r"^\s*\w+\s*=\s*[{\[\(\"']"), # assignment with literal
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
def _is_code_line(line: str) -> bool:
|
||||||
|
"""Check if a line looks like code."""
|
||||||
|
return any(p.match(line) for p in CODE_PATTERNS)
|
||||||
|
|
||||||
|
|
||||||
|
def _is_json_content(text: str) -> bool:
|
||||||
|
"""Check if content is valid JSON."""
|
||||||
|
try:
|
||||||
|
json.loads(text)
|
||||||
|
return True
|
||||||
|
except (json.JSONDecodeError, ValueError):
|
||||||
|
return False
|
||||||
|
|
||||||
|
|
||||||
|
def _is_yaml_content(lines: list[str]) -> bool:
|
||||||
|
"""Heuristic: check if content looks like YAML."""
|
||||||
|
yaml_indicators = 0
|
||||||
|
for line in lines[:30]:
|
||||||
|
stripped = line.strip()
|
||||||
|
if stripped.startswith("---"):
|
||||||
|
yaml_indicators += 1
|
||||||
|
elif re.match(r"^\w[\w\s]*:\s", stripped):
|
||||||
|
yaml_indicators += 1
|
||||||
|
elif stripped.startswith("- ") and ":" in stripped:
|
||||||
|
yaml_indicators += 1
|
||||||
|
# If most non-empty lines look like YAML
|
||||||
|
non_empty = sum(1 for l in lines[:30] if l.strip())
|
||||||
|
return non_empty > 0 and yaml_indicators / non_empty > 0.6
|
||||||
|
|
||||||
|
|
||||||
|
def detect_file_type(filepath: Path) -> str:
|
||||||
|
"""Classify a file as 'natural_language', 'code', 'config', or 'unknown'.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
One of: 'natural_language', 'code', 'config', 'unknown'
|
||||||
|
"""
|
||||||
|
ext = filepath.suffix.lower()
|
||||||
|
|
||||||
|
# Known code filenames win over any extension rule
|
||||||
|
if filepath.name.lower() in KNOWN_CODE_FILENAMES:
|
||||||
|
return "code"
|
||||||
|
|
||||||
|
# Extension-based classification
|
||||||
|
if ext in COMPRESSIBLE_EXTENSIONS:
|
||||||
|
return "natural_language"
|
||||||
|
if ext in SKIP_EXTENSIONS:
|
||||||
|
return "code" if ext not in {".json", ".yaml", ".yml", ".toml", ".ini", ".cfg", ".env"} else "config"
|
||||||
|
|
||||||
|
# Extensionless files (like CLAUDE.md, TODO) — check content
|
||||||
|
if not ext:
|
||||||
|
try:
|
||||||
|
text = filepath.read_text(encoding="utf-8", errors="ignore")
|
||||||
|
except (OSError, PermissionError):
|
||||||
|
return "unknown"
|
||||||
|
|
||||||
|
lines = text.splitlines()[:50]
|
||||||
|
|
||||||
|
# Shebang means executable script, never prose
|
||||||
|
if text.startswith("#!"):
|
||||||
|
return "code"
|
||||||
|
|
||||||
|
if _is_json_content(text[:10000]):
|
||||||
|
return "config"
|
||||||
|
if _is_yaml_content(lines):
|
||||||
|
return "config"
|
||||||
|
|
||||||
|
code_lines = sum(1 for l in lines if l.strip() and _is_code_line(l))
|
||||||
|
non_empty = sum(1 for l in lines if l.strip())
|
||||||
|
if non_empty > 0 and code_lines / non_empty > 0.4:
|
||||||
|
return "code"
|
||||||
|
|
||||||
|
return "natural_language"
|
||||||
|
|
||||||
|
return "unknown"
|
||||||
|
|
||||||
|
|
||||||
|
def should_compress(filepath: Path) -> bool:
|
||||||
|
"""Return True if the file is natural language and should be compressed."""
|
||||||
|
if not filepath.is_file():
|
||||||
|
return False
|
||||||
|
# Skip backup files
|
||||||
|
if filepath.name.endswith(".original.md"):
|
||||||
|
return False
|
||||||
|
return detect_file_type(filepath) == "natural_language"
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
import sys
|
||||||
|
|
||||||
|
if len(sys.argv) < 2:
|
||||||
|
print("Usage: python detect.py <file1> [file2] ...")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
for path_str in sys.argv[1:]:
|
||||||
|
p = Path(path_str).resolve()
|
||||||
|
file_type = detect_file_type(p)
|
||||||
|
compress = should_compress(p)
|
||||||
|
print(f" {p.name:30s} type={file_type:20s} compress={compress}")
|
||||||
@@ -0,0 +1,434 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
import re
|
||||||
|
from collections import Counter
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
URL_REGEX = re.compile(r"https?://[^\s)`]+") # a backtick is never part of a URL
|
||||||
|
FENCE_OPEN_REGEX = re.compile(r"^(\s{0,3})(`{3,}|~{3,})(.*)$")
|
||||||
|
|
||||||
|
# A line that is nothing but a fence marker plus an optional info string, at ANY
|
||||||
|
# indentation. Used ONLY to scrub leaked markers before inline-code pairing (see
|
||||||
|
# extract_inline_codes) — never for block extraction.
|
||||||
|
#
|
||||||
|
# Widening FENCE_OPEN_REGEX itself to `\s*` looks like the obvious fix for #820
|
||||||
|
# and is a net regression: a lone indented ``` (the natural way to SHOW a fence
|
||||||
|
# inside prose) then opens a block that runs to EOF, swallowing real code blocks
|
||||||
|
# and silently removing their inline spans from validation. That turns a
|
||||||
|
# false-failure bug into a false-PASS bug, and a false PASS overwrites the
|
||||||
|
# user's file with unvalidated output.
|
||||||
|
FENCE_MARKER_LINE_REGEX = re.compile(r"^\s*(?:`{3,}|~{3,})[^`~]*$")
|
||||||
|
|
||||||
|
# Cap on how much of a lost/added span is echoed in an error message. Unpaired
|
||||||
|
# backticks can make a "span" hundreds of characters of prose; printing it whole
|
||||||
|
# is what made #820's failures undiagnosable.
|
||||||
|
MAX_REPORTED_SPAN = 60
|
||||||
|
HEADING_REGEX = re.compile(r"^(#{1,6})\s+(.*)", re.MULTILINE)
|
||||||
|
BULLET_REGEX = re.compile(r"^\s*[-*+]\s+", re.MULTILINE)
|
||||||
|
# Any list item, ordered or not. Four spaces inside a list item is the item's
|
||||||
|
# content indentation, never an indented code block.
|
||||||
|
LIST_ITEM_REGEX = re.compile(r"^\s*(?:[-*+]|\d+[.)])\s")
|
||||||
|
|
||||||
|
# crude but effective path detection
|
||||||
|
# Requires either a path prefix (./ ../ / or drive letter) or a slash/backslash within the match
|
||||||
|
PATH_REGEX = re.compile(r"(?:\./|\.\./|/|[A-Za-z]:\\)[\w\-/\\\.]+|[\w\-\.]+[/\\][\w\-/\\\.]+")
|
||||||
|
|
||||||
|
# PATH_REGEX is crude on purpose and also matches ordinary prose pairs —
|
||||||
|
# "pros/cons", "Node/browser", "state/lifecycle". Caveman prose ADDS those
|
||||||
|
# constructions freely and dropping one breaks nothing, so only an unambiguous
|
||||||
|
# path — a leading ./ ../ / or drive letter, or a dotted filename in the last
|
||||||
|
# component — is treated as a hard loss.
|
||||||
|
DEFINITE_PATH_REGEX = re.compile(r"^(?:\./|\.\./|/|[A-Za-z]:\\)|[^/\\]*\.[A-Za-z0-9]{1,8}$")
|
||||||
|
|
||||||
|
|
||||||
|
class ValidationResult:
|
||||||
|
def __init__(self):
|
||||||
|
self.is_valid = True
|
||||||
|
self.errors = []
|
||||||
|
self.warnings = []
|
||||||
|
|
||||||
|
def add_error(self, msg):
|
||||||
|
self.is_valid = False
|
||||||
|
self.errors.append(msg)
|
||||||
|
|
||||||
|
def add_warning(self, msg):
|
||||||
|
self.warnings.append(msg)
|
||||||
|
|
||||||
|
|
||||||
|
def read_file(path: Path) -> str:
|
||||||
|
return path.read_text(encoding="utf-8")
|
||||||
|
|
||||||
|
|
||||||
|
# ---------- Extractors ----------
|
||||||
|
|
||||||
|
|
||||||
|
def extract_headings(text):
|
||||||
|
return [(level, title.strip()) for level, title in HEADING_REGEX.findall(text)]
|
||||||
|
|
||||||
|
|
||||||
|
def extract_code_blocks(text):
|
||||||
|
"""Line-based fenced code block extractor.
|
||||||
|
|
||||||
|
Handles ``` and ~~~ fences with variable length (CommonMark: closing
|
||||||
|
fence must use same char and be at least as long as opening). Supports
|
||||||
|
nested fences (e.g. an outer 4-backtick block wrapping inner 3-backtick
|
||||||
|
content).
|
||||||
|
|
||||||
|
Merges fenced and indented blocks by their DOCUMENT POSITION, not by
|
||||||
|
type. validate_code_blocks compares this list positionally (c1 != c2),
|
||||||
|
so a type-grouped return (all fenced, then all indented) makes two
|
||||||
|
blocks that swapped RELATIVE order in the document produce the same
|
||||||
|
list on both sides: the comparison passes while the invariant it
|
||||||
|
exists to check (block order preserved) has actually been violated.
|
||||||
|
"""
|
||||||
|
blocks = []
|
||||||
|
lines = text.split("\n")
|
||||||
|
i = 0
|
||||||
|
n = len(lines)
|
||||||
|
while i < n:
|
||||||
|
m = FENCE_OPEN_REGEX.match(lines[i])
|
||||||
|
if not m:
|
||||||
|
i += 1
|
||||||
|
continue
|
||||||
|
start = i
|
||||||
|
fence_char = m.group(2)[0]
|
||||||
|
fence_len = len(m.group(2))
|
||||||
|
open_line = lines[i]
|
||||||
|
block_lines = [open_line]
|
||||||
|
i += 1
|
||||||
|
closed = False
|
||||||
|
while i < n:
|
||||||
|
close_m = FENCE_OPEN_REGEX.match(lines[i])
|
||||||
|
if (
|
||||||
|
close_m
|
||||||
|
and close_m.group(2)[0] == fence_char
|
||||||
|
and len(close_m.group(2)) >= fence_len
|
||||||
|
and close_m.group(3).strip() == ""
|
||||||
|
):
|
||||||
|
block_lines.append(lines[i])
|
||||||
|
closed = True
|
||||||
|
i += 1
|
||||||
|
break
|
||||||
|
block_lines.append(lines[i])
|
||||||
|
i += 1
|
||||||
|
if closed:
|
||||||
|
blocks.append((start, "\n".join(block_lines)))
|
||||||
|
# Unclosed fences are silently skipped — they indicate malformed markdown
|
||||||
|
# and including them would cause false-positive validation failures.
|
||||||
|
ordered = sorted(blocks + extract_indented_code_blocks(text), key=lambda pair: pair[0])
|
||||||
|
return [block_text for _, block_text in ordered]
|
||||||
|
|
||||||
|
|
||||||
|
def extract_indented_code_blocks(text):
|
||||||
|
"""CommonMark indented code blocks — 4-space-indented runs outside any fence.
|
||||||
|
|
||||||
|
Without these, ` kubectl delete pod --all -n prod` was prose to the
|
||||||
|
validator: "code blocks preserved exactly" compared empty to empty and
|
||||||
|
PASSED while the compressor rewrote the command to
|
||||||
|
`kubectl delete pod -n dev`. A clean pass on a mutated destructive command
|
||||||
|
is the worst failure this tool has, because it overwrites the user's file.
|
||||||
|
|
||||||
|
Deliberately conservative about lists: inside a list item, four spaces are
|
||||||
|
the item's content indentation, not code, and nested bullets are ordinary
|
||||||
|
prose the compressor SHOULD rewrite. A run is only treated as code when the
|
||||||
|
document is not inside a list and the run is preceded by a blank line — so
|
||||||
|
this adds detections, it never turns existing passes into false failures.
|
||||||
|
|
||||||
|
Returns (start_line, text) pairs rather than bare text: extract_code_blocks
|
||||||
|
needs each block's document position to merge it with fenced blocks in
|
||||||
|
order (see that function's docstring).
|
||||||
|
"""
|
||||||
|
blocks = []
|
||||||
|
lines = text.split("\n")
|
||||||
|
fenced = set()
|
||||||
|
for block in extract_fenced_spans(lines):
|
||||||
|
fenced.update(block)
|
||||||
|
in_list = False
|
||||||
|
previous_blank = True
|
||||||
|
i = 0
|
||||||
|
n = len(lines)
|
||||||
|
while i < n:
|
||||||
|
line = lines[i]
|
||||||
|
stripped = line.strip()
|
||||||
|
if i in fenced:
|
||||||
|
in_list, previous_blank = in_list, False
|
||||||
|
i += 1
|
||||||
|
continue
|
||||||
|
if not stripped:
|
||||||
|
previous_blank = True
|
||||||
|
i += 1
|
||||||
|
continue
|
||||||
|
indent = len(line) - len(line.lstrip(" \t"))
|
||||||
|
if LIST_ITEM_REGEX.match(line):
|
||||||
|
in_list = True
|
||||||
|
elif indent == 0:
|
||||||
|
in_list = False
|
||||||
|
if not in_list and previous_blank and indent >= 4:
|
||||||
|
start = i
|
||||||
|
run = []
|
||||||
|
while i < n and i not in fenced:
|
||||||
|
current = lines[i]
|
||||||
|
if not current.strip():
|
||||||
|
# A blank line continues an indented block only if more
|
||||||
|
# indented content follows.
|
||||||
|
lookahead = i + 1
|
||||||
|
while lookahead < n and not lines[lookahead].strip():
|
||||||
|
lookahead += 1
|
||||||
|
if lookahead < n and lookahead not in fenced and \
|
||||||
|
len(lines[lookahead]) - len(lines[lookahead].lstrip(" \t")) >= 4:
|
||||||
|
run.extend(lines[i:lookahead])
|
||||||
|
i = lookahead
|
||||||
|
continue
|
||||||
|
break
|
||||||
|
if len(current) - len(current.lstrip(" \t")) < 4:
|
||||||
|
break
|
||||||
|
run.append(current)
|
||||||
|
i += 1
|
||||||
|
if run:
|
||||||
|
blocks.append((start, "\n".join(run)))
|
||||||
|
previous_blank = False
|
||||||
|
continue
|
||||||
|
previous_blank = False
|
||||||
|
i += 1
|
||||||
|
return blocks
|
||||||
|
|
||||||
|
|
||||||
|
def extract_fenced_spans(lines):
|
||||||
|
"""Line-index ranges covered by fenced blocks, so indented-code detection
|
||||||
|
never reaches inside one."""
|
||||||
|
spans = []
|
||||||
|
i = 0
|
||||||
|
n = len(lines)
|
||||||
|
while i < n:
|
||||||
|
m = FENCE_OPEN_REGEX.match(lines[i])
|
||||||
|
if not m:
|
||||||
|
i += 1
|
||||||
|
continue
|
||||||
|
fence_char = m.group(2)[0]
|
||||||
|
fence_len = len(m.group(2))
|
||||||
|
start = i
|
||||||
|
i += 1
|
||||||
|
while i < n:
|
||||||
|
close_m = FENCE_OPEN_REGEX.match(lines[i])
|
||||||
|
if (
|
||||||
|
close_m
|
||||||
|
and close_m.group(2)[0] == fence_char
|
||||||
|
and len(close_m.group(2)) >= fence_len
|
||||||
|
and close_m.group(3).strip() == ""
|
||||||
|
):
|
||||||
|
i += 1
|
||||||
|
break
|
||||||
|
i += 1
|
||||||
|
spans.append(range(start, i))
|
||||||
|
return spans
|
||||||
|
|
||||||
|
|
||||||
|
def extract_urls(text):
|
||||||
|
return set(URL_REGEX.findall(text))
|
||||||
|
|
||||||
|
|
||||||
|
def extract_paths(text):
|
||||||
|
return set(PATH_REGEX.findall(text))
|
||||||
|
|
||||||
|
|
||||||
|
def count_bullets(text):
|
||||||
|
return len(BULLET_REGEX.findall(text))
|
||||||
|
|
||||||
|
|
||||||
|
def extract_inline_codes(text):
|
||||||
|
"""Backtick-delimited inline spans, with fenced code blocks stripped first.
|
||||||
|
|
||||||
|
Previously used a column-0-anchored regex to strip fences, which misses
|
||||||
|
fences indented 1-3 spaces (valid CommonMark). Reuse extract_code_blocks
|
||||||
|
(FENCE_OPEN_REGEX-based, indentation-aware) instead so an indented fence's
|
||||||
|
body backticks don't leak into inline-code pairing.
|
||||||
|
|
||||||
|
Any fence-marker line that survives that pass is then blanked (#820). A
|
||||||
|
fence indented 4+ spaces — what you get from showing an example inside a
|
||||||
|
bullet — is not matched by FENCE_OPEN_REGEX, so extract_code_blocks does
|
||||||
|
not remove it and its OWN backticks used to leak in and shift the pairing
|
||||||
|
of every following span, making the file permanently uncompressible.
|
||||||
|
Blanking just the marker lines fixes that without removing any prose, and
|
||||||
|
cannot run away the way a widened fence opener does.
|
||||||
|
|
||||||
|
The span pattern deliberately still spans newlines. CommonMark permits a
|
||||||
|
line ending inside a code span and hard-wrapped markdown produces them, so
|
||||||
|
a single-line pattern silently drops real spans — which downgrades a
|
||||||
|
deleted or mutated span from error to PASS. Long/garbled spans are a
|
||||||
|
presentation problem, handled by truncating in the error message instead.
|
||||||
|
"""
|
||||||
|
text_without_fences = text
|
||||||
|
for block in extract_code_blocks(text):
|
||||||
|
text_without_fences = text_without_fences.replace(block, "", 1)
|
||||||
|
text_without_fences = "\n".join(
|
||||||
|
"" if FENCE_MARKER_LINE_REGEX.match(line) else line
|
||||||
|
for line in text_without_fences.split("\n")
|
||||||
|
)
|
||||||
|
# Run-aware pairing (CommonMark): a span opens with a backtick run and
|
||||||
|
# closes with an equal-length run. A mid-line ``` in prose ("inside a
|
||||||
|
# ```diff fence") has no equal closer, so it matches nothing — instead of
|
||||||
|
# its trailing backtick shifting the pairing of every following span.
|
||||||
|
# The opener is the WHOLE run (`(?!`)` after it), so a lone ``` can never
|
||||||
|
# shrink to a single backtick and pair with the next span. The content may
|
||||||
|
# hold a run of a different length (``a`b``), so it is "anything, lazily"
|
||||||
|
# up to the first equal run, not "anything but a backtick"; DOTALL keeps
|
||||||
|
# hard-wrapped spans in the comparison set.
|
||||||
|
return [
|
||||||
|
m.group(2)
|
||||||
|
for m in re.finditer(r"(?<!`)(`+)(?!`)(.+?)(?<!`)\1(?!`)", text_without_fences, re.DOTALL)
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
# ---------- Validators ----------
|
||||||
|
|
||||||
|
|
||||||
|
def validate_headings(orig, comp, result):
|
||||||
|
h1 = extract_headings(orig)
|
||||||
|
h2 = extract_headings(comp)
|
||||||
|
|
||||||
|
# Changed heading TEXT is an error, not a warning. Every in-document anchor
|
||||||
|
# link points at a heading's slug, so renaming "# Configuration Options" to
|
||||||
|
# "# Config" silently breaks all of them — and SKILL.md and CLAUDE.md both
|
||||||
|
# state headings are preserved. Only counts used to gate the overwrite, so
|
||||||
|
# a run that renamed every heading reported "Validation passed". A level-only
|
||||||
|
# change keeps every slug intact and stays a warning.
|
||||||
|
if len(h1) != len(h2):
|
||||||
|
result.add_error(f"Heading count mismatch: {len(h1)} vs {len(h2)}")
|
||||||
|
return
|
||||||
|
|
||||||
|
t1 = [text for _, text in h1]
|
||||||
|
t2 = [text for _, text in h2]
|
||||||
|
if t1 != t2:
|
||||||
|
lost = [t for t in t1 if t not in t2]
|
||||||
|
added = [t for t in t2 if t not in t1]
|
||||||
|
result.add_error(f"Heading text/order changed: lost={lost}, added={added}")
|
||||||
|
elif h1 != h2:
|
||||||
|
# Same text, different level. The outline moved but no anchor broke —
|
||||||
|
# slugs come from the text, so links still resolve.
|
||||||
|
result.add_warning("Heading levels changed")
|
||||||
|
|
||||||
|
|
||||||
|
def validate_code_blocks(orig, comp, result):
|
||||||
|
c1 = extract_code_blocks(orig)
|
||||||
|
c2 = extract_code_blocks(comp)
|
||||||
|
|
||||||
|
if c1 != c2:
|
||||||
|
result.add_error("Code blocks not preserved exactly")
|
||||||
|
|
||||||
|
|
||||||
|
def validate_urls(orig, comp, result):
|
||||||
|
u1 = extract_urls(orig)
|
||||||
|
u2 = extract_urls(comp)
|
||||||
|
|
||||||
|
if u1 != u2:
|
||||||
|
result.add_error(f"URL mismatch: lost={u1 - u2}, added={u2 - u1}")
|
||||||
|
|
||||||
|
|
||||||
|
def validate_paths(orig, comp, result):
|
||||||
|
"""File paths are preserved — an error, never a warning.
|
||||||
|
|
||||||
|
This validator never called add_error at all, so a compressed file that had
|
||||||
|
dropped `src/hooks/caveman-config.js` still reported "Validation passed" and
|
||||||
|
the in-place overwrite stood. SKILL.md and CLAUDE.md both promise paths
|
||||||
|
survive compression; nothing enforced it.
|
||||||
|
"""
|
||||||
|
p1 = extract_paths(orig)
|
||||||
|
p2 = extract_paths(comp)
|
||||||
|
lost = p1 - p2
|
||||||
|
added = p2 - p1
|
||||||
|
|
||||||
|
definite = {p for p in lost if DEFINITE_PATH_REGEX.search(p)}
|
||||||
|
if definite:
|
||||||
|
result.add_error(f"File paths lost: {sorted(definite)}")
|
||||||
|
if (lost - definite) or added:
|
||||||
|
result.add_warning(f"Path mismatch: lost={sorted(lost)}, added={sorted(added)}")
|
||||||
|
|
||||||
|
|
||||||
|
def validate_bullets(orig, comp, result):
|
||||||
|
b1 = count_bullets(orig)
|
||||||
|
b2 = count_bullets(comp)
|
||||||
|
|
||||||
|
if b1 == 0:
|
||||||
|
return
|
||||||
|
|
||||||
|
diff = abs(b1 - b2) / b1
|
||||||
|
|
||||||
|
if diff > 0.15:
|
||||||
|
result.add_warning(f"Bullet count changed too much: {b1} -> {b2}")
|
||||||
|
|
||||||
|
|
||||||
|
def validate_inline_codes(orig, comp, result):
|
||||||
|
def _render_spans(spans):
|
||||||
|
"""Render spans for an error message, truncated and newline-escaped.
|
||||||
|
|
||||||
|
A span may legitimately contain newlines, and an unpaired backtick can
|
||||||
|
make one hundreds of characters of prose. Printing those whole is what
|
||||||
|
made #820's failures undiagnosable — but the fix belongs here, in
|
||||||
|
presentation, not in what counts as a span.
|
||||||
|
"""
|
||||||
|
out = []
|
||||||
|
for span in sorted(spans):
|
||||||
|
flat = span.replace("\n", "\\n")
|
||||||
|
if len(flat) > MAX_REPORTED_SPAN:
|
||||||
|
flat = flat[:MAX_REPORTED_SPAN] + "…"
|
||||||
|
out.append(repr(flat))
|
||||||
|
return "{" + ", ".join(out) + "}"
|
||||||
|
|
||||||
|
c1 = Counter(extract_inline_codes(orig))
|
||||||
|
c2 = Counter(extract_inline_codes(comp))
|
||||||
|
|
||||||
|
if c1 != c2:
|
||||||
|
lost = set(c1.keys()) - set(c2.keys())
|
||||||
|
added = set(c2.keys()) - set(c1.keys())
|
||||||
|
for code, count in c1.items():
|
||||||
|
if code in c2 and c2[code] < count:
|
||||||
|
lost.add(f"{code} (lost {count - c2[code]} of {count} occurrences)")
|
||||||
|
if lost:
|
||||||
|
result.add_error(f"Inline code lost: {_render_spans(lost)}")
|
||||||
|
if added:
|
||||||
|
result.add_warning(f"Inline code added: {_render_spans(added)}")
|
||||||
|
|
||||||
|
|
||||||
|
# ---------- Main ----------
|
||||||
|
|
||||||
|
|
||||||
|
def validate(original_path: Path, compressed_path: Path) -> ValidationResult:
|
||||||
|
result = ValidationResult()
|
||||||
|
|
||||||
|
orig = read_file(original_path)
|
||||||
|
comp = read_file(compressed_path)
|
||||||
|
|
||||||
|
validate_headings(orig, comp, result)
|
||||||
|
validate_code_blocks(orig, comp, result)
|
||||||
|
validate_urls(orig, comp, result)
|
||||||
|
validate_paths(orig, comp, result)
|
||||||
|
validate_bullets(orig, comp, result)
|
||||||
|
validate_inline_codes(orig, comp, result)
|
||||||
|
|
||||||
|
return result
|
||||||
|
|
||||||
|
|
||||||
|
# ---------- CLI ----------
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
import sys
|
||||||
|
|
||||||
|
if len(sys.argv) != 3:
|
||||||
|
print("Usage: python validate.py <original> <compressed>")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
orig = Path(sys.argv[1]).resolve()
|
||||||
|
comp = Path(sys.argv[2]).resolve()
|
||||||
|
|
||||||
|
res = validate(orig, comp)
|
||||||
|
|
||||||
|
print(f"\nValid: {res.is_valid}")
|
||||||
|
|
||||||
|
if res.errors:
|
||||||
|
print("\nErrors:")
|
||||||
|
for e in res.errors:
|
||||||
|
print(f" - {e}")
|
||||||
|
|
||||||
|
if res.warnings:
|
||||||
|
print("\nWarnings:")
|
||||||
|
for w in res.warnings:
|
||||||
|
print(f" - {w}")
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
---
|
||||||
|
name: caveman-discover
|
||||||
|
description: >
|
||||||
|
Find and label every LLM workflow in the repository so Caveman Cloud groups
|
||||||
|
spend by workflow instead of one bucket. Use for "discover workflows" or
|
||||||
|
breaking LLM spend down by workflow.
|
||||||
|
---
|
||||||
|
|
||||||
|
You are labeling this repository's LLM workflows for Caveman Cloud. A
|
||||||
|
*workflow* is a job the code performs — "answer a support ticket", "build the
|
||||||
|
nightly digest", "run the eval suite" — not a technology. Every gateway
|
||||||
|
request can carry a workflow label; unlabeled traffic all lands in one
|
||||||
|
`unlabeled-workflow` bucket. Your job: find the workflows, name them well,
|
||||||
|
wire the labels, and verify nothing broke.
|
||||||
|
|
||||||
|
This changes code, so it goes through the user's normal review: **propose the
|
||||||
|
table first, apply after the user agrees.** Re-running on an already-labeled
|
||||||
|
repo must change nothing (idempotent).
|
||||||
|
|
||||||
|
This skill is operator-invoked. An `unlabeled-traffic` Cave Plan observation is
|
||||||
|
review-only and does not create an advisory file, proposal, or Draft PR. Do not
|
||||||
|
infer that telemetry selected a callsite or authorized an edit. Independently
|
||||||
|
inventory the repository, present the labeling table, and wait for the user's
|
||||||
|
approval before changing code.
|
||||||
|
|
||||||
|
## Step 1 — Inventory the workflows
|
||||||
|
|
||||||
|
Walk the repo from its entry points, not from its imports:
|
||||||
|
|
||||||
|
- HTTP/RPC handlers that call an LLM (directly or through layers)
|
||||||
|
- Scheduled jobs: cron definitions, queue consumers, workers, GitHub Actions
|
||||||
|
that invoke LLM code
|
||||||
|
- CLI commands and scripts (`scripts/`, `bin/`, package.json scripts)
|
||||||
|
- Eval / test harnesses that burn real tokens
|
||||||
|
- Distinct agents or chains inside a framework (each LangGraph graph, each
|
||||||
|
crew, each agent definition is usually its own workflow)
|
||||||
|
|
||||||
|
One workflow = one job a human would name. Ten callsites inside the same
|
||||||
|
request handler are one workflow; one shared `llm.ts` helper used by three
|
||||||
|
jobs is three workflows (label at the callers, never the shared helper).
|
||||||
|
|
||||||
|
## Step 2 — Name them
|
||||||
|
|
||||||
|
Slug grammar (the gateway enforces this): lowercase `[a-z0-9_-]`, 1–96 chars.
|
||||||
|
Name the job, not the tech:
|
||||||
|
|
||||||
|
- Good: `support-reply`, `nightly-digest`, `pr-review`, `eval-suite`,
|
||||||
|
`onboarding-email`
|
||||||
|
- Bad: `openai-calls` (tech), `main` (says nothing), `SupportReply` (invalid),
|
||||||
|
`johns-test-3` (won't age)
|
||||||
|
|
||||||
|
Names are forever-ish — renaming later splits the spend history. When a job's
|
||||||
|
purpose isn't clear from the code, derive the slug from the file name and mark
|
||||||
|
it `review` in the table rather than inventing a purpose.
|
||||||
|
|
||||||
|
## Step 3 — Propose, then apply
|
||||||
|
|
||||||
|
Present this table and ask to proceed:
|
||||||
|
|
||||||
|
```
|
||||||
|
| workflow | job | where | how it gets labeled |
|
||||||
|
|---|---|---|---|
|
||||||
|
| support-reply | answers inbound tickets | src/bot/reply.ts:41 | defaultHeaders on the reply client |
|
||||||
|
| nightly-digest | 02:00 summary job | jobs/digest.ts:12 | header on the digest client |
|
||||||
|
| eval-suite (review) | scripts/eval.ts:8 — purpose inferred from filename | scripts/eval.ts:8 | env override at invocation |
|
||||||
|
```
|
||||||
|
|
||||||
|
Then wire each label with the lightest mechanism available at that callsite:
|
||||||
|
|
||||||
|
- **@caveman-ai/sdk / caveman_cloud SDK**: per-trace `workflow` option, or
|
||||||
|
`defaultWorkflow` on the client a single-job service constructs.
|
||||||
|
- **Raw provider SDKs** (OpenAI/Anthropic/LangChain/LiteLLM/Vercel): add
|
||||||
|
`"x-cave-workflow": "<slug>"` to the same `defaultHeaders` /
|
||||||
|
`default_headers` / `extra_headers` block that already carries
|
||||||
|
`x-cave-api-key`. Shared client used by several jobs → pass the header per
|
||||||
|
call (every SDK above accepts per-request header overrides), or give each
|
||||||
|
job its own thin client.
|
||||||
|
- **Wrapped coding agents** (`caveman wrap`): `--workflow <slug>` flag or
|
||||||
|
`CAVE_WORKFLOW=<slug>` env at the invocation site (cron line, CI step).
|
||||||
|
- **Raw HTTP**: add the `x-cave-workflow` header to the request.
|
||||||
|
|
||||||
|
Label the callers, keep the diff minimal, match the repo's style. If a
|
||||||
|
callsite is not routed through the Caveman gateway at all, don't label it —
|
||||||
|
list it under "not wired" in the report (labels only travel on gateway
|
||||||
|
traffic; wiring is the caveman-setup skill's job).
|
||||||
|
|
||||||
|
## Step 4 — Verify
|
||||||
|
|
||||||
|
Run whatever the repo already uses to exercise one labeled path (a test, a
|
||||||
|
dev script, one curl). Then confirm: the request still succeeds (the gateway
|
||||||
|
rejects an invalid label with 400 `cave_invalid_request_header` — fix the slug
|
||||||
|
if so). Labeled spend appears on the dashboard at `/activity?tab=workflows` as
|
||||||
|
each workflow next runs; jobs on a schedule show up when the schedule fires,
|
||||||
|
and that's worth saying in the report rather than pretending they're live.
|
||||||
|
|
||||||
|
## Step 5 — Report
|
||||||
|
|
||||||
|
```
|
||||||
|
## Workflows labeled
|
||||||
|
|
||||||
|
| workflow | job | where |
|
||||||
|
|---|---|---|
|
||||||
|
| support-reply | answers inbound tickets | src/bot/reply.ts:41 |
|
||||||
|
| nightly-digest | 02:00 summary job | jobs/digest.ts:12 |
|
||||||
|
|
||||||
|
Verified: <the labeled path you actually exercised, and what you observed>
|
||||||
|
Lands at: <DASHBOARD>/activity?tab=workflows — each row appears as that workflow
|
||||||
|
next runs. Anything still unlabeled shows as `unlabeled-workflow`.
|
||||||
|
Not wired (no gateway routing, so no label): <list or "none">
|
||||||
|
Marked review: <slugs whose purpose was inferred from filenames, or "none">
|
||||||
|
```
|
||||||
|
|
||||||
|
If you found no LLM entry points at all: say exactly that, and point at the
|
||||||
|
setup skill (`<docs origin>/docs/agent-setup.md`) instead of manufacturing a
|
||||||
|
table.
|
||||||
@@ -0,0 +1,142 @@
|
|||||||
|
---
|
||||||
|
name: caveman-evidence-review
|
||||||
|
description: >
|
||||||
|
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows,
|
||||||
|
traces, latency, errors, routing, savings. Use when asked what Caveman found
|
||||||
|
or where LLM spend goes.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Review Caveman evidence
|
||||||
|
|
||||||
|
Act as a read-only operator. Build conclusions from current Caveman data, not
|
||||||
|
from repository guesses. Never start, approve, cancel, or roll back an
|
||||||
|
experiment from this skill.
|
||||||
|
|
||||||
|
## Hard rules
|
||||||
|
|
||||||
|
1. Keep these buckets separate:
|
||||||
|
- measured provider-complete list-price cost;
|
||||||
|
- `inferred` daily headroom;
|
||||||
|
- `verified` ledger savings;
|
||||||
|
- evidence cost.
|
||||||
|
Never add or relabel them.
|
||||||
|
2. Do not fetch prompt, completion, tool, or artifact payloads unless the user
|
||||||
|
explicitly asks for payload review. Metadata, spans, timing, models, token
|
||||||
|
counts, status, and optimizer attribution are enough for the default review.
|
||||||
|
3. Scope every read to the project selected by Caveman context. Never supply an
|
||||||
|
organization id.
|
||||||
|
4. Empty results are evidence of no current signal, not zero cost or zero risk.
|
||||||
|
5. Cite trace ids and exact time windows used. Do not claim a cause from an
|
||||||
|
aggregate alone.
|
||||||
|
|
||||||
|
## Step 1 — Load context
|
||||||
|
|
||||||
|
Prefer MCP:
|
||||||
|
|
||||||
|
```text
|
||||||
|
caveman_context {}
|
||||||
|
```
|
||||||
|
|
||||||
|
CLI fallback:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman cloud whoami
|
||||||
|
caveman cloud projects list
|
||||||
|
```
|
||||||
|
|
||||||
|
Stop if login or project selection is missing. Ask the user to run
|
||||||
|
`caveman login` or select a project; never guess.
|
||||||
|
|
||||||
|
## Step 2 — Establish baseline
|
||||||
|
|
||||||
|
Use `caveman_report` for:
|
||||||
|
|
||||||
|
- `overview`
|
||||||
|
- `costs`
|
||||||
|
- `score`
|
||||||
|
- `workflows`
|
||||||
|
- `verified_savings`
|
||||||
|
|
||||||
|
Then use `caveman_plan` for ranked daily headroom. If question is narrow, skip
|
||||||
|
unrelated reports. Read shortest set that can answer it.
|
||||||
|
|
||||||
|
CLI fallback:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman cloud costs
|
||||||
|
caveman cloud score
|
||||||
|
caveman cloud plan --json
|
||||||
|
```
|
||||||
|
|
||||||
|
State report window and basis before interpreting direction.
|
||||||
|
|
||||||
|
## Step 3 — Test the leading explanation with traces
|
||||||
|
|
||||||
|
Use `caveman_trace_search`. Choose a bounded window and closed filters:
|
||||||
|
workflow, agent, model, provider, error code, runtime mode, cache status,
|
||||||
|
optimization id, status class, token/cost/latency bounds, compression, or
|
||||||
|
monitor verdict.
|
||||||
|
|
||||||
|
Useful groupings:
|
||||||
|
|
||||||
|
- `workflow` — find jobs driving cost or failures;
|
||||||
|
- `model` — compare model mix;
|
||||||
|
- `session` — isolate retry or loop behavior;
|
||||||
|
- ungrouped — identify exact traces.
|
||||||
|
|
||||||
|
Compare a suspect cohort with a control cohort or earlier bounded window.
|
||||||
|
Do not infer causality from one expensive trace.
|
||||||
|
|
||||||
|
CLI fallback:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman cloud traces search \
|
||||||
|
--workflow <slug> \
|
||||||
|
--from <RFC3339> \
|
||||||
|
--to <RFC3339> \
|
||||||
|
--sort total_cost_usd \
|
||||||
|
--dir desc \
|
||||||
|
--limit 25
|
||||||
|
```
|
||||||
|
|
||||||
|
## Step 4 — Inspect representative traces
|
||||||
|
|
||||||
|
Call `caveman_trace_get` for a small number of high-signal trace ids. Inspect
|
||||||
|
request and span metadata, latency, status, token counts, cache state, applied
|
||||||
|
optimizers, and model route. Keep payload retrieval off.
|
||||||
|
|
||||||
|
CLI fallback:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman cloud traces show <trace-id> --spans
|
||||||
|
```
|
||||||
|
|
||||||
|
## Step 5 — Report
|
||||||
|
|
||||||
|
Use this shape:
|
||||||
|
|
||||||
|
```text
|
||||||
|
## Caveman evidence review
|
||||||
|
|
||||||
|
Scope: <project> · <from> to <to>
|
||||||
|
Measured cost: <value and basis>
|
||||||
|
Verified savings: <ledger value, kept separate>
|
||||||
|
Inferred headroom: <per-day band, kept separate>
|
||||||
|
|
||||||
|
Findings:
|
||||||
|
1. <finding> — <aggregate evidence> — traces <ids>
|
||||||
|
2. <finding> — <aggregate evidence> — traces <ids>
|
||||||
|
|
||||||
|
Unproven:
|
||||||
|
- <plausible explanation lacking a control, trace, or eval>
|
||||||
|
|
||||||
|
Next read-only check:
|
||||||
|
- <one bounded query>
|
||||||
|
|
||||||
|
Possible action:
|
||||||
|
- <proposal only; use caveman-manage for read-only lifecycle review and safety gate>
|
||||||
|
```
|
||||||
|
|
||||||
|
If data is missing, name missing signal and stop at strongest supported
|
||||||
|
statement. Never turn a catalog subtotal into an invoice or an experiment result
|
||||||
|
into verified savings.
|
||||||
@@ -0,0 +1,42 @@
|
|||||||
|
---
|
||||||
|
name: caveman-explore
|
||||||
|
description: Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
|
||||||
|
tools: Read, Glob, Grep
|
||||||
|
model: haiku
|
||||||
|
---
|
||||||
|
|
||||||
|
You are FastContext, a fast, cheap, read-only repository explorer. Another agent
|
||||||
|
(the solver) delegates a localization question to you. Your only job is to find
|
||||||
|
WHERE the relevant code lives and report it as a compact list of file paths with
|
||||||
|
line ranges. You never edit files, run commands, or propose a solution.
|
||||||
|
|
||||||
|
How to work:
|
||||||
|
|
||||||
|
1. Issue several tool calls IN PARALLEL in your first turn — cast a broad net.
|
||||||
|
Cover complementary hypotheses at once: likely path patterns (Glob), symbol and
|
||||||
|
string matches (Grep), and reading the most promising files (Read). Do not probe
|
||||||
|
one file at a time when you can fan out.
|
||||||
|
2. Follow the evidence over one or two more turns only if needed. Stop as soon as
|
||||||
|
you can name the relevant locations. You are optimizing for the solver's token
|
||||||
|
budget, so finish fast.
|
||||||
|
3. Only cite line ranges you actually read. Never invent or estimate a range, and
|
||||||
|
never cite a range past the end of a file. A precise small range beats a vague
|
||||||
|
large one.
|
||||||
|
|
||||||
|
Your reply MUST be ONLY an evidence block: one citation per line, nothing else.
|
||||||
|
No preamble, no explanation, no summary, no markdown headings. Use exactly this
|
||||||
|
shape, one per line:
|
||||||
|
|
||||||
|
path/to/file.ext:START-END reason it is relevant
|
||||||
|
|
||||||
|
Example reply:
|
||||||
|
|
||||||
|
src/router/pick.go:42-71 route selection — where a model is chosen
|
||||||
|
src/router/pick_test.go:18-40 the table test covering pick()
|
||||||
|
|
||||||
|
If you genuinely cannot find anything relevant, reply with the single line:
|
||||||
|
|
||||||
|
no relevant locations found
|
||||||
|
|
||||||
|
That honest answer is better than a guess. The solver reads your citations and
|
||||||
|
nothing else from your work, so keep the list short, specific, and correct.
|
||||||
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"name": "@caveman/skill-caveman-explore",
|
||||||
|
"version": "1.0.0",
|
||||||
|
"license": "Apache-2.0",
|
||||||
|
"private": true,
|
||||||
|
"type": "module",
|
||||||
|
"description": "Read-only FastContext exploration skill with parallel repository search and citation-only output.",
|
||||||
|
"files": ["SKILL.md"],
|
||||||
|
"scripts": {
|
||||||
|
"test": "node --test --test-force-exit tests/*.mjs"
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,44 @@
|
|||||||
|
import { test } from "node:test";
|
||||||
|
import assert from "node:assert";
|
||||||
|
import { readFileSync } from "node:fs";
|
||||||
|
import { dirname, join } from "node:path";
|
||||||
|
import { fileURLToPath } from "node:url";
|
||||||
|
|
||||||
|
const skillFile = join(dirname(fileURLToPath(import.meta.url)), "..", "SKILL.md");
|
||||||
|
const md = readFileSync(skillFile, "utf8");
|
||||||
|
|
||||||
|
function frontmatter(text) {
|
||||||
|
const match = text.match(/^---\n([\s\S]*?)\n---\n/);
|
||||||
|
assert.ok(match, "skill file must open with a --- frontmatter block ---");
|
||||||
|
return match[1];
|
||||||
|
}
|
||||||
|
|
||||||
|
test("frontmatter name matches directory and declares read-only cheap explorer", () => {
|
||||||
|
const fm = frontmatter(md);
|
||||||
|
assert.match(fm, /^name:\s*caveman-explore\s*$/m, "name must be caveman-explore");
|
||||||
|
assert.match(fm, /^model:\s*haiku\s*$/m, "explorer must run on cheap model");
|
||||||
|
assert.match(fm, /^tools:\s*Read,\s*Glob,\s*Grep\s*$/m, "tools must be exactly three read-only tools");
|
||||||
|
assert.doesNotMatch(fm, /\b(Edit|Write|Bash|NotebookEdit)\b/, "explorer must not have write or execution tools");
|
||||||
|
assert.match(fm, /^description:\s*.+/m, "description required for auto-delegation");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("description says when to invoke and skip", () => {
|
||||||
|
const fm = frontmatter(md);
|
||||||
|
assert.match(fm, /cold-start|cross-file|localization|search has failed/i, "must say when to invoke");
|
||||||
|
assert.match(fm, /skip/i, "must say when to skip");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("body mandates parallel calls and citation-only reply", () => {
|
||||||
|
assert.match(md, /IN PARALLEL/i, "must mandate parallel tool calls");
|
||||||
|
assert.match(md, /ONLY an evidence block|only.*citation/i, "must mandate citation-only reply");
|
||||||
|
assert.match(md, /path\/to\/file\.ext:START-END/i, "must show compact path:line shape");
|
||||||
|
assert.match(md, /no relevant locations found/i, "must give honest empty fallback");
|
||||||
|
assert.match(md, /never edit|never.*solve|read-only/i, "must forbid editing and solving");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("artifact carries no placeholder markers", () => {
|
||||||
|
const banned = ["TO" + "DO", "FIX" + "ME", "place" + "holder", "X" + "X" + "X"];
|
||||||
|
for (const marker of banned) {
|
||||||
|
assert.doesNotMatch(md, new RegExp("\\b" + marker + "\\b", "i"), `artifact must not contain ${marker}`);
|
||||||
|
}
|
||||||
|
});
|
||||||
@@ -0,0 +1,39 @@
|
|||||||
|
# caveman-help
|
||||||
|
|
||||||
|
Quick-reference card. One shot, no mode change.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Prints a cheat sheet of all caveman modes, sibling skills, deactivation triggers, and how to set the default mode via env var or config file. One-shot display — does not flip the active mode, write flag files, or persist anything. Use when you forget the slash commands.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-help
|
||||||
|
```
|
||||||
|
|
||||||
|
Also triggers on "caveman help", "what caveman commands", "how do I use caveman".
|
||||||
|
|
||||||
|
## Example output
|
||||||
|
|
||||||
|
```
|
||||||
|
Modes:
|
||||||
|
/caveman the voice (default)
|
||||||
|
/ultracave grammar stripped
|
||||||
|
/megacave classical Chinese
|
||||||
|
/caveman status report the mode, change nothing
|
||||||
|
|
||||||
|
Skills:
|
||||||
|
/caveman-commit terse Conventional Commits
|
||||||
|
/caveman-review one-line PR comments
|
||||||
|
/caveman-compress smaller Markdown memory files
|
||||||
|
/caveman-stats recorded token usage (savings unknown)
|
||||||
|
|
||||||
|
Deactivate:
|
||||||
|
"stop caveman" or "normal mode"
|
||||||
|
```
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md) — full reference card
|
||||||
|
- [Caveman README](../../README.md) — repo overview
|
||||||
@@ -0,0 +1,62 @@
|
|||||||
|
---
|
||||||
|
name: caveman-help
|
||||||
|
description: >
|
||||||
|
Quick-reference card for the three caveman skills and their commands.
|
||||||
|
Trigger: /caveman-help or "caveman help".
|
||||||
|
---
|
||||||
|
|
||||||
|
# Caveman Help
|
||||||
|
|
||||||
|
Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.
|
||||||
|
|
||||||
|
## Modes
|
||||||
|
|
||||||
|
| Mode | Trigger | What change |
|
||||||
|
|------|---------|-------------|
|
||||||
|
| **caveman** | `/caveman` | The voice. Answer first, no fluff, every fact kept. Default. |
|
||||||
|
| **ultracave** | `/ultracave` (alias `/caveman ultra`) | Grammar stripped. Fragments, one word when enough, each fact once. |
|
||||||
|
| **megacave** | `/megacave` (alias `/caveman wenyan`) | Classical Chinese 文言文. Far fewer characters, technical terms verbatim. |
|
||||||
|
|
||||||
|
Mode stick until changed or session end.
|
||||||
|
`/caveman status` reports current mode without changing it. Claude Code and the standalone OpenCode plugin read stored state; other hosts answer from the conversation and mark it `(not tracked by this host)`.
|
||||||
|
|
||||||
|
## Skills
|
||||||
|
|
||||||
|
| Skill | Trigger | What it do |
|
||||||
|
|-------|---------|-----------|
|
||||||
|
| **caveman-commit** | `/caveman-commit` | Terse commit messages. Conventional Commits. ≤50 char subject. |
|
||||||
|
| **caveman-review** | `/caveman-review` | One-line PR comments: `L42: bug: user null. Add guard.` |
|
||||||
|
| **caveman-compress** | `/caveman-compress <file>` | Compress .md files to caveman prose. 33.2% fewer tokens on the repo's five test files. |
|
||||||
|
| **caveman-help** | `/caveman-help` | This card. |
|
||||||
|
|
||||||
|
## Deactivate
|
||||||
|
|
||||||
|
Say "stop caveman" or "normal mode". Resume anytime with `/caveman`.
|
||||||
|
|
||||||
|
## Language
|
||||||
|
|
||||||
|
Keep user's language by default — reply in the language user writes, never switch regardless of example text or multilingual context elsewhere. Compress the style, not the language. Technical terms, code, commands, commit types, and exact error strings stay verbatim unless user ask for translation.
|
||||||
|
|
||||||
|
## Configure Default Mode
|
||||||
|
|
||||||
|
Default mode = `caveman`. Change it:
|
||||||
|
|
||||||
|
**Environment variable** (highest priority):
|
||||||
|
```bash
|
||||||
|
export CAVEMAN_DEFAULT_MODE=ultracave
|
||||||
|
```
|
||||||
|
|
||||||
|
**Config file** (`~/.config/caveman/config.json`):
|
||||||
|
```json
|
||||||
|
{ "defaultMode": "ultracave" }
|
||||||
|
```
|
||||||
|
|
||||||
|
For opt-in activation in Claude Code, set `defaultMode` to `manual`. Sessions start off; `/caveman` or `talk like caveman` activates caveman. `off` also disables bare-command activation. `manual` is a startup policy, not a mode. OpenCode still starts in caveman mode because its installer also supplies static activation rules.
|
||||||
|
|
||||||
|
Set `"off"` to suppress automatic and bare-command activation. Use `"manual"` when bare `/caveman` should activate.
|
||||||
|
|
||||||
|
Resolution: env var > repo config > user config > `caveman`. Legacy values `lite`, `full`, `ultra`, `wenyan*` still resolve.
|
||||||
|
|
||||||
|
## More
|
||||||
|
|
||||||
|
Full docs: https://github.com/JuliusBrussee/caveman
|
||||||
@@ -0,0 +1,32 @@
|
|||||||
|
# skills/caveman-learn — the Caveman Learn editing skill (Apache-2.0, public)
|
||||||
|
|
||||||
|
The consent-gated half of `caveman learn`. The analyzer (the Go proxy) **measures**
|
||||||
|
where an agent's tokens go and writes a ranked plan; this skill is what an agent
|
||||||
|
loads to **act** on that plan — proposing each fix and applying it only with the
|
||||||
|
user's per-edit yes. It is the loop-closer the learn spec §10
|
||||||
|
describes, plus the new `cavemem_offload` move.
|
||||||
|
|
||||||
|
## Layout
|
||||||
|
- `SKILL.md` — the canonical skill body (frontmatter `name: caveman-learn` + a
|
||||||
|
trigger-phrase `description`; body = the read-plan → per-class consent loop). This
|
||||||
|
file is the source of truth.
|
||||||
|
- `tests/skill-file.test.mjs` — asserts the canonical file is well-formed and honest
|
||||||
|
(frontmatter present; the net-token-negative gate, the never-make-the-agent-dumber
|
||||||
|
guard, consent-per-edit, and reversibility are all stated; no imperative for
|
||||||
|
behavioral findings; no placeholders).
|
||||||
|
|
||||||
|
## Install path
|
||||||
|
`caveman tools skills install caveman-learn` (in `../../cli/src/index.ts`) writes this file
|
||||||
|
into a repo's `.claude/skills/caveman-learn/SKILL.md` (Claude Code) or
|
||||||
|
`~/.codex/skills/caveman-learn/SKILL.md` (Codex). The CLI **embeds a byte-identical copy**
|
||||||
|
(`CAVEMAN_LEARN_SKILL_MD`) because the published CLI ships no sibling assets;
|
||||||
|
`../../cli/tests/skills.runtime.mjs` asserts the embedded copy equals this canonical
|
||||||
|
file (the drift guard). **Change this file and that constant together.**
|
||||||
|
|
||||||
|
## Boundary (binding)
|
||||||
|
The skill — using the agent's own file tools — is the ONLY thing that edits a user's
|
||||||
|
config. `caveman learn apply` stays read-only (it materializes candidates), and
|
||||||
|
`caveman mem *` are mechanical store ops. The offload move enforces a net-token-negative
|
||||||
|
gate and the never-make-the-agent-dumber guard before any trim.
|
||||||
|
|
||||||
|
See ../../mem/CLAUDE.md (cavemem) · ../caveman-explore/SKILL.md (the packaging precedent)
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
# caveman-learn skill
|
||||||
|
|
||||||
|
Close the loop on `caveman learn`. The command finds where your agent's tokens
|
||||||
|
go; this skill walks through the findings with you and applies the fixes, one
|
||||||
|
approved edit at a time.
|
||||||
|
|
||||||
|
## Install
|
||||||
|
|
||||||
|
caveman skills install caveman-learn # this repo's .claude/skills
|
||||||
|
caveman skills install caveman-learn --user # all repos (~/.claude/skills)
|
||||||
|
caveman skills install caveman-learn --agent codex
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
1. Runs `caveman learn report --json` and shows your Setup Score and the
|
||||||
|
findings, biggest first.
|
||||||
|
2. For each finding you pick, it proposes a fix and asks yes or no:
|
||||||
|
- **Safe fix** (a heavy CLAUDE.md, a skill you never use): a concrete trim.
|
||||||
|
It is kept only if it measurably makes every message smaller.
|
||||||
|
- **Repeated text** (text you paste again in session after session): move it
|
||||||
|
to **Caveman memory** (cavemem). The full text is stored once, the agent
|
||||||
|
recalls a short version when it needs it, and a small pointer stays
|
||||||
|
behind. Kept only when it beats pasting, and only after a test recall
|
||||||
|
proves the text still comes back.
|
||||||
|
- **Needed** (setup your agent relies on): never touched.
|
||||||
|
|
||||||
|
After an approved edit passes its re-check, `caveman learn applied <id>`
|
||||||
|
records which finding was fixed, how, when, and its size before. Later scans
|
||||||
|
compare the sessions after the fix and report `improved`, `unchanged`,
|
||||||
|
`regressed`, or `insufficient_data` (not enough sessions yet). This record
|
||||||
|
does not edit your own or your repository's files.
|
||||||
|
|
||||||
|
## Honesty
|
||||||
|
|
||||||
|
Everything is an estimate (`inferred`): no currency, never "verified". Every
|
||||||
|
edit waits for your yes and can be undone. A move to memory that would leave
|
||||||
|
the agent unable to recall the text is rejected. `caveman learn` itself never
|
||||||
|
edits your files; this skill does, and only with your yes.
|
||||||
@@ -0,0 +1,174 @@
|
|||||||
|
---
|
||||||
|
name: caveman-learn
|
||||||
|
description: Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
|
||||||
|
---
|
||||||
|
|
||||||
|
You are the Caveman Learn editing skill. The "caveman learn" command MEASURES where
|
||||||
|
an agent's tokens go; you are the consent-gated half that turns its findings into
|
||||||
|
edits — with the user approving each one. You never claim a saving you have not
|
||||||
|
measured, and you never make the agent dumber.
|
||||||
|
|
||||||
|
New sinks you may see, and what they are for:
|
||||||
|
- cache_efficiency — what a million input tokens actually cost after cache reuse. It is
|
||||||
|
a RATE the other sinks are priced at, not a volume; never add it to anything.
|
||||||
|
- tool_output_portfolio — the call shapes that dominate context, ranked.
|
||||||
|
- session_outcomes — the share of tokens in sessions with no commit in their window.
|
||||||
|
Correlational. Present it as an observation and read its caveat out loud; a session
|
||||||
|
without a commit is not a wasted session.
|
||||||
|
- subagent_spend — the share of context that ran in subagents. Visibility only. Do not
|
||||||
|
turn it into advice to spawn fewer subagents.
|
||||||
|
- procedure_repeat:* — a distillation candidate. See SKILL_DISTILLATION below.
|
||||||
|
|
||||||
|
Read the plan first:
|
||||||
|
|
||||||
|
1. Run: caveman learn report --json
|
||||||
|
Parse the caveman.learn.v1 JSON. Show the Cave Score, its four components, and the
|
||||||
|
ranked token sinks. For each sink state its class and basis. Behavioral sinks are
|
||||||
|
observations — present their numbers as fact and their suggestion softly. Do not
|
||||||
|
turn a behavioral finding into an imperative.
|
||||||
|
|
||||||
|
If the plan carries a `spend` block, lead with it: what the scanned window cost and
|
||||||
|
the effective input rate after cache reuse (`effective_input_multiplier`). Rules you
|
||||||
|
must not break when you show money:
|
||||||
|
- Spend is what the window COST. It is never what a fix would return.
|
||||||
|
- Say the window it covers. Never multiply it into a month, a year, or a run rate.
|
||||||
|
- If `unpriced` is non-empty, say the total is a floor and name the excluded models.
|
||||||
|
- Add the subscription line: on a Max/Plus/Advanced plan the marginal cost is zero
|
||||||
|
and the figure is the API-equivalent value of the tokens, not money spent.
|
||||||
|
- Never call any of it verified.
|
||||||
|
|
||||||
|
Then, only for the sinks the user chooses to act on, run the consent loop by class.
|
||||||
|
|
||||||
|
Before proposing a fix, you may run: caveman learn simulate <sink_id>. Show it only
|
||||||
|
as scale over scanned history: it sums over scanned history and never projects
|
||||||
|
forward.
|
||||||
|
|
||||||
|
REDUCIBLE (a heavy CLAUDE.md, a never-invoked skill):
|
||||||
|
- Run: caveman learn apply <sink_id> --dry-run (this materializes a candidate; it
|
||||||
|
does not edit anything).
|
||||||
|
- Propose a concrete diff and show before -> after tokens/turn.
|
||||||
|
- Ask the user yes or no. On yes, apply the edit with your own file tools.
|
||||||
|
- Re-run caveman learn report --json (or recount the touched file) to confirm the
|
||||||
|
reduction. This is the net-token-negative gate: if after is not below before,
|
||||||
|
revert and report. Never keep an edit that does not reduce tokens/turn.
|
||||||
|
|
||||||
|
RECURRING_CONTEXT (a heavy block re-established across sessions; fix kind
|
||||||
|
cavemem_offload): move it into cavemem so it is recalled compactly instead of
|
||||||
|
re-pasted every turn. The candidate carries only a LOCATOR — never the block body.
|
||||||
|
- Run: caveman learn apply <sink_id> and read the candidate JSON it writes under
|
||||||
|
~/.caveman/candidates/. Take only the locator, the numbers, and the proposed pointer
|
||||||
|
text. Do not trust any body from the candidate; there is none.
|
||||||
|
- Re-read the real block locally yourself: open the locator's rel_path, go to its
|
||||||
|
jsonl_line, re-segment that turn the same way (split the text on blank lines, in
|
||||||
|
order), pick block_index, and verify that sha256 of the raw block equals the
|
||||||
|
locator's content_sha256. If it does not match, the file changed since the scan —
|
||||||
|
abort this item.
|
||||||
|
- Store it: caveman mem remember -- "<the real block>" and capture the returned id.
|
||||||
|
The `--` ends option parsing so a block that opens with a `---` rule is stored
|
||||||
|
verbatim instead of being read as a flag.
|
||||||
|
- Measure the gate honestly. before = the block's tokens/turn (it loaded every turn).
|
||||||
|
after = the pointer's tokens/turn plus the recall cost. Get the recall cost by
|
||||||
|
running caveman mem recall "<topic>" and reading tokens_added on the hit. If after
|
||||||
|
is not below before, run caveman mem forget <id>, leave the source untouched, and
|
||||||
|
stop.
|
||||||
|
- Trim the source and write the pointer. Remove the block from its CLAUDE.md or
|
||||||
|
AGENTS.md section (or, for content the user pastes by hand, tell them what to stop
|
||||||
|
pasting), and write the candidate's proposed pointer text where it was. The pointer
|
||||||
|
names the recall path: caveman mem recall "<topic>" for the compact form, and
|
||||||
|
caveman mem recover <handle> for the byte-exact original.
|
||||||
|
- Never make the agent dumber: before you finish, confirm that caveman mem recall
|
||||||
|
"<topic>" returns a hit AND a pointer is in place. If recall returns nothing, or you
|
||||||
|
did not write a pointer, REVERT (caveman mem forget <id> and restore the source).
|
||||||
|
Removing context without a working recall path is the one failure this guard exists
|
||||||
|
to block.
|
||||||
|
- Re-measure and report the confirmed reduction and the recall path.
|
||||||
|
|
||||||
|
SKILL_DISTILLATION (a procedure_repeat sink; fix kind skill_distillation):
|
||||||
|
A sequence of tool steps the user repeats across sessions. Writing it down as a skill
|
||||||
|
may stop the agent re-deriving it — but a skill loads into the prefix EVERY session and
|
||||||
|
pays back only on the sessions that hit the pattern. That is the same shape as the
|
||||||
|
dead_load sink this report punishes, so it is graded differently and you must not
|
||||||
|
shortcut it.
|
||||||
|
- Never apply this through the net-token-negative gate. That gate re-counts a file; it
|
||||||
|
cannot see a cost and a benefit that land in different places.
|
||||||
|
- Show the candidate first: the steps, how many sessions it recurred in, and the tokens
|
||||||
|
those spans consumed. Say plainly that the payback is unproven.
|
||||||
|
- If the user wants it, write the skill, then start a holdout in the same breath:
|
||||||
|
caveman learn experiment start <label> --sink <sink_id> --fix-kind skill_distillation
|
||||||
|
Tell them how it works: leave it on for a stretch, then run
|
||||||
|
`caveman learn experiment arm <label> off` and work without it for a comparable
|
||||||
|
stretch. Each arm needs at least 5 sessions before any verdict exists.
|
||||||
|
- Read the result with `caveman learn experiment report <label>`. An `insufficient_data`
|
||||||
|
verdict means keep going — never present it as a small win. A `regressed` verdict means
|
||||||
|
delete the skill; say so directly.
|
||||||
|
- The harness compares median tokens per session. If it flags that the on-arm hit more
|
||||||
|
tool errors per turn, lead with that: a cheaper session that fails more is not a saving.
|
||||||
|
|
||||||
|
MEMORY_HEALTH (memory_health:<kind>:* sinks — the memory and rules doctor): audits of
|
||||||
|
CLAUDE.md, CLAUDE.local.md, .claude/rules, AGENTS.md, GEMINI.md and Claude Code auto
|
||||||
|
memory (MEMORY.md plus its topic files). Every item is one edit, one yes. Never delete
|
||||||
|
memory content without the user's yes.
|
||||||
|
- duplicate_rules — reducible. The same rule loads from two files every turn. Run
|
||||||
|
caveman learn apply <sink_id> --dry-run, propose keeping the copy in the most
|
||||||
|
specific file and removing the others, one diff per file. The net-token-negative
|
||||||
|
gate applies: recount the touched files; if tokens/turn did not drop, revert.
|
||||||
|
- memory_orphans — memory files the index never links, and index links to missing
|
||||||
|
files. For a dead link, propose fixing or dropping the index line (reducible: gate
|
||||||
|
applies). For an orphan file, show its first lines and ask: link it from MEMORY.md,
|
||||||
|
or retire it. Linking adds index tokens — say so; that edit is outside the gate.
|
||||||
|
- memory_truncation — MEMORY.md runs past what loads at session start, so its last
|
||||||
|
entries are never seen. Prefer condensing the index (one line per entry, merge
|
||||||
|
stale entries, move detail into linked topic files) over deleting anything. Show
|
||||||
|
the new index and its line count against the limit before writing.
|
||||||
|
- broken_imports — an @import points at nothing. For each one ask whether to fix the
|
||||||
|
path (show the candidate file you found) or remove the import.
|
||||||
|
- stale_references — a backticked repo path no longer exists. Behavioral: show the
|
||||||
|
line and where the file likely moved; update or drop only on a yes.
|
||||||
|
- buried_rules — a heuristic, and say so. Offer to move the listed emphatic rules
|
||||||
|
nearer the top; never rewrite their wording.
|
||||||
|
|
||||||
|
LOAD_BEARING: never touch. It appears in the report only so the score stays honest.
|
||||||
|
|
||||||
|
Reporting savings (caveman learn savings):
|
||||||
|
|
||||||
|
The ledger shows what applied fixes returned, grouped by HOW it was measured. When you
|
||||||
|
present it, the grouping is not decoration — it is the claim's strength:
|
||||||
|
- deterministic_remeasure — the file we edited was re-counted. Strongest local rung.
|
||||||
|
- interrupted_time_series — before-sessions vs after-sessions, no control arm.
|
||||||
|
- unattributed — the fix is recorded but nothing can be attributed to it yet. Not a
|
||||||
|
saving; say so.
|
||||||
|
|
||||||
|
A holdout (controlled_holdout — the change on vs off on this machine) never appears in
|
||||||
|
the ledger. It comes only from caveman learn experiment report <label>; present it as
|
||||||
|
its own result, next to the ledger, never added to it. No command produces a
|
||||||
|
counterfactual_replay row yet, so never claim one.
|
||||||
|
|
||||||
|
Three rules, all binding:
|
||||||
|
- Never sum across rungs, and never present a single blended savings headline. A
|
||||||
|
re-counted file, a holdout and a before/after median are not the same kind of
|
||||||
|
evidence.
|
||||||
|
- Always read out the `confounders` on a row you are presenting as a win. They are
|
||||||
|
standing caveats, not fine print, and they exist precisely for the good-news case.
|
||||||
|
- Read `attribution.provenance`. `intact` means the file still carries the edit we
|
||||||
|
proposed. `changed_since` means someone edited past it and part of the delta is not
|
||||||
|
ours — say so. `target_missing` means the delta cannot be tied to the fix at all.
|
||||||
|
`not_fingerprinted` means the fix predates fingerprinting, so the edit's presence is
|
||||||
|
unverified. Experiments carry `not_applicable`: there is no single edit to check.
|
||||||
|
Never present a `changed_since` or `target_missing` row as a caveman result.
|
||||||
|
|
||||||
|
A regression carries no dollar figure by design. Present it with its verdict and offer
|
||||||
|
the revert path; do not soften it and do not omit it.
|
||||||
|
|
||||||
|
Binding rules:
|
||||||
|
- Consent per edit. No "apply all" that hides the individual diffs.
|
||||||
|
- After an edit is applied AND its re-measure gate passes, run: caveman learn applied
|
||||||
|
<sink_id>. Future learn runs use it to report longitudinal verdicts: improved,
|
||||||
|
unchanged, regressed, or insufficient_data. Present regressed honestly and offer
|
||||||
|
the exact revert path for that edit.
|
||||||
|
- Every edit is reversible: report exactly what you changed. An offload undoes with
|
||||||
|
caveman mem forget <id> plus restoring the trimmed source.
|
||||||
|
- inferred only. Never present a local number as verified. Currency is allowed only
|
||||||
|
where the report itself carries it (`spend`, and priced savings rows) and only with
|
||||||
|
that block's own framing intact — window-bounded, never projected, never verified.
|
||||||
|
- The analyzer (caveman learn) is read-only. You are the only writer, and only after a
|
||||||
|
yes.
|
||||||
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"name": "@caveman/skill-caveman-learn",
|
||||||
|
"version": "1.0.0",
|
||||||
|
"license": "Apache-2.0",
|
||||||
|
"private": true,
|
||||||
|
"type": "module",
|
||||||
|
"description": "Consent-gated editing skill that closes the loop on a Caveman learn report: review ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit approval, a net-token-negative gate, and a never-make-the-agent-dumber guard.",
|
||||||
|
"files": ["SKILL.md"],
|
||||||
|
"scripts": {
|
||||||
|
"test": "node --test --test-force-exit tests/*.mjs"
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1 @@
|
|||||||
|
import "./skill-file.test.mjs";
|
||||||
@@ -0,0 +1,52 @@
|
|||||||
|
import { test } from "node:test";
|
||||||
|
import assert from "node:assert";
|
||||||
|
import { readFileSync } from "node:fs";
|
||||||
|
import { dirname, join } from "node:path";
|
||||||
|
import { fileURLToPath } from "node:url";
|
||||||
|
|
||||||
|
const skill = readFileSync(
|
||||||
|
join(dirname(fileURLToPath(import.meta.url)), "..", "SKILL.md"),
|
||||||
|
"utf8",
|
||||||
|
);
|
||||||
|
|
||||||
|
test("SKILL.md has valid frontmatter", () => {
|
||||||
|
assert.match(skill, /^---\nname: caveman-learn\n/, "must declare name: caveman-learn");
|
||||||
|
assert.match(skill, /\ndescription: .+\n---/s, "must carry a description");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("SKILL.md states the binding honesty rules", () => {
|
||||||
|
assert.match(skill, /net-token-negative gate/i, "must state the net-token-negative gate");
|
||||||
|
assert.match(skill, /never make the agent dumber/i, "must state the dumber-guard");
|
||||||
|
assert.match(skill, /consent per edit/i, "must require per-edit consent");
|
||||||
|
assert.match(skill, /reversible/i, "must require reversibility");
|
||||||
|
assert.match(skill, /inferred only/i, "must keep findings inferred");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("SKILL.md covers the cavemem_offload move", () => {
|
||||||
|
assert.match(skill, /cavemem_offload/, "must describe the offload fix kind");
|
||||||
|
assert.match(skill, /content_sha256/, "must verify the block against its content hash");
|
||||||
|
assert.match(skill, /caveman mem recover/, "must name the byte-exact recovery path");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("SKILL.md closes the longitudinal outcome loop honestly", () => {
|
||||||
|
assert.match(skill, /caveman learn applied\s+<sink_id>/, "must record a fix only after it passes re-measurement");
|
||||||
|
assert.match(skill, /improved,\s+unchanged, regressed, or insufficient_data/, "must name every longitudinal verdict");
|
||||||
|
assert.match(skill, /Present regressed honestly and offer\s+the exact revert path/, "must disclose regressions and offer reversal");
|
||||||
|
assert.match(skill, /caveman learn simulate <sink_id>/, "may show counterfactual history before a proposal");
|
||||||
|
assert.match(skill, /sums over scanned history and never projects\s+forward/, "must not project simulation results");
|
||||||
|
});
|
||||||
|
|
||||||
|
test("SKILL.md never turns a behavioral finding into an imperative", () => {
|
||||||
|
for (const banned of ["you don't need", "you over-use", "you overuse", "$"]) {
|
||||||
|
assert.ok(!skill.includes(banned), `SKILL.md must not contain ${JSON.stringify(banned)}`);
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
|
test("SKILL.md has no placeholders", () => {
|
||||||
|
// Build the markers from fragments so this assertion file does not itself trip
|
||||||
|
// the repo's no-placeholder scan (which greps for the literal words).
|
||||||
|
const markers = ["TO" + "DO", "FIX" + "ME", "XXX", "PLACE" + "HOLDER", "TK" + "TK"];
|
||||||
|
for (const banned of markers) {
|
||||||
|
assert.ok(!skill.includes(banned), `SKILL.md must not contain ${banned}`);
|
||||||
|
}
|
||||||
|
});
|
||||||
@@ -0,0 +1,112 @@
|
|||||||
|
---
|
||||||
|
name: caveman-manage
|
||||||
|
description: >
|
||||||
|
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use
|
||||||
|
when asked to start, approve, cancel, promote or roll back a Caveman
|
||||||
|
experiment.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Manage eval-gated experiments
|
||||||
|
|
||||||
|
Treat every lifecycle change as a production control action. Read current state
|
||||||
|
and results, then report one supported recommendation or block.
|
||||||
|
Current agent MCP is intentionally read-only: control-api does not yet enforce a
|
||||||
|
complete lifecycle transition table and evidence gate atomically.
|
||||||
|
|
||||||
|
## Non-negotiable gates
|
||||||
|
|
||||||
|
1. A request to review, inspect, explain, or recommend authorizes reads only.
|
||||||
|
2. Never approve an experiment whose results are pending, whose required
|
||||||
|
guardrails are absent, or whose evidence reports a breach.
|
||||||
|
3. Never convert experiment lift into `verified_savings`. Only active real
|
||||||
|
traffic plus provider-causal, provider-complete ledger evidence can do that.
|
||||||
|
4. Never supply an organization id. Project and tenant scope come from the
|
||||||
|
logged-in Caveman identity and server RBAC.
|
||||||
|
5. Never execute a lifecycle mutation, even after user approval. Exact
|
||||||
|
`<action>:<experiment_id>` strings are agent-generatable and are not proof of
|
||||||
|
human intent.
|
||||||
|
6. Unknown states and server errors fail closed. Report exact
|
||||||
|
`cave_snake_code`.
|
||||||
|
|
||||||
|
## Step 1 — Load project and experiment
|
||||||
|
|
||||||
|
Prefer MCP:
|
||||||
|
|
||||||
|
```text
|
||||||
|
caveman_context {}
|
||||||
|
caveman_experiment_get {"action":"get","experiment_id":"<id>"}
|
||||||
|
caveman_experiment_get {"action":"results","experiment_id":"<id>"}
|
||||||
|
```
|
||||||
|
|
||||||
|
Use `{"action":"list"}` when the user has not named an id.
|
||||||
|
|
||||||
|
CLI fallback:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman cloud experiments list
|
||||||
|
caveman cloud experiments show <id>
|
||||||
|
caveman cloud experiments results <id>
|
||||||
|
```
|
||||||
|
|
||||||
|
Stop if login, project, experiment, or results are unavailable.
|
||||||
|
|
||||||
|
## Step 2 — Evaluate evidence
|
||||||
|
|
||||||
|
Report:
|
||||||
|
|
||||||
|
- current lifecycle state and safety class;
|
||||||
|
- control and candidate sample sizes;
|
||||||
|
- quality or eval result;
|
||||||
|
- latency, error, cost, retry, drop, and escalation guardrails when present;
|
||||||
|
- evidence cost;
|
||||||
|
- rollback or hold reason;
|
||||||
|
- whether result is pending, failed, promotable, or active.
|
||||||
|
|
||||||
|
Absence is not a pass. If a required field is absent, state
|
||||||
|
`evidence incomplete` and do not propose approval.
|
||||||
|
|
||||||
|
## Step 3 — Propose one action
|
||||||
|
|
||||||
|
Allowed actions:
|
||||||
|
|
||||||
|
- `start` — only from a startable draft or queued state with configured graders;
|
||||||
|
- `approve` — only with complete passing evidence and a safety class the
|
||||||
|
current role may approve;
|
||||||
|
- `cancel` — stop a non-active experiment the user no longer wants;
|
||||||
|
- `rollback` — revert an active or harmful change through the server's linked
|
||||||
|
policy path. Current deployments may reject this honestly with
|
||||||
|
`cave_not_implemented`; never describe that response as a rollback.
|
||||||
|
|
||||||
|
Show recommendation and id:
|
||||||
|
|
||||||
|
```text
|
||||||
|
Proposed action: approve experiment 7f...
|
||||||
|
Reason: candidate passed quality and every configured guardrail.
|
||||||
|
Execution: blocked until server-authoritative lifecycle and evidence gates ship.
|
||||||
|
```
|
||||||
|
|
||||||
|
Do not treat earlier generic statements such as "manage it" or "do what is best"
|
||||||
|
as mutation approval.
|
||||||
|
|
||||||
|
## Step 4 — Block unsafe execution
|
||||||
|
|
||||||
|
Do not emit or run an executable lifecycle command. Explain that current server
|
||||||
|
does not yet enforce every evidence/state transition atomically. CLI and MCP
|
||||||
|
agent surfaces therefore expose experiment reads only.
|
||||||
|
|
||||||
|
## Step 5 — Re-read after external operator action
|
||||||
|
|
||||||
|
If operator says they executed command, read detail and results again. Report
|
||||||
|
server-observed post-state, audit or result response, and any policy-delivery
|
||||||
|
status returned. Never infer success from operator intent alone.
|
||||||
|
|
||||||
|
Use this close:
|
||||||
|
|
||||||
|
```text
|
||||||
|
Action: <action> <experiment-id>
|
||||||
|
Before: <state>
|
||||||
|
Server response: <status and cave_snake_code if any>
|
||||||
|
After: <re-read state>
|
||||||
|
Basis: experiment evidence only. Verified savings unchanged unless the signed
|
||||||
|
ledger independently records active, provider-causal real-traffic savings.
|
||||||
|
```
|
||||||
@@ -0,0 +1,111 @@
|
|||||||
|
---
|
||||||
|
name: caveman-optimize
|
||||||
|
description: >
|
||||||
|
Turn a Caveman optimization observation into an operator-chosen candidate
|
||||||
|
with a paired baseline evaluation. Use when asked to inspect or evaluate a
|
||||||
|
Caveman optimization report. Needs explicit approval.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Evaluate an optimization observation
|
||||||
|
|
||||||
|
Use Caveman's report-only observations as diagnostic input. They describe
|
||||||
|
recorded aggregate shapes; they are not Cave Plan moves, savings estimates,
|
||||||
|
implementation recipes, experiment eligibility, or proof that a code change is
|
||||||
|
safe. Keep the workflow operator-chosen and evidence-first.
|
||||||
|
|
||||||
|
## 1. Read the exact observations
|
||||||
|
|
||||||
|
Require a logged-in Caveman CLI session and run:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
caveman opportunities list
|
||||||
|
```
|
||||||
|
|
||||||
|
Read only the `report_only_observations` array. Do not select from the lifecycle
|
||||||
|
`data` array. Preserve each server-provided `title` and `observation` verbatim.
|
||||||
|
Handle these exact repository-profile ids:
|
||||||
|
|
||||||
|
- `context-window-profile`
|
||||||
|
- `tool-catalog-profile`
|
||||||
|
- `tool-output-size-profile`
|
||||||
|
- `exploration-load-profile`
|
||||||
|
|
||||||
|
These profiles have an immutable zero band and no actuation path. Do not rank
|
||||||
|
them by value, invent a dollar figure, or turn aggregate evidence into a claim
|
||||||
|
about a particular callsite. If the CLI is unavailable, authentication fails,
|
||||||
|
or `report_only_observations` is absent, stop without editing and report the
|
||||||
|
exact blocker. Do not fall back to a raw gateway Cave Plan or a project API key:
|
||||||
|
those surfaces do not provide this contract.
|
||||||
|
|
||||||
|
Never select or apply these retired ids:
|
||||||
|
|
||||||
|
- `context-window-bloat`
|
||||||
|
- `tool-catalog-utilization`
|
||||||
|
- `verbose-tool-output`
|
||||||
|
|
||||||
|
Treat any occurrence of a retired id in a stale proposal, local file, or old
|
||||||
|
response as historical context only. Never revive its money, recipe, or
|
||||||
|
lifecycle claim. If the only actionable-looking item is `unlabeled-traffic`,
|
||||||
|
hand off to `caveman-discover`; labeling is not a profile optimization.
|
||||||
|
|
||||||
|
## 2. Ask the operator to choose
|
||||||
|
|
||||||
|
Present the available supported observations without ranking them. Include the
|
||||||
|
id, the exact title, the exact observation, and `last_seen_at`. Ask for an
|
||||||
|
**explicit operator choice** before inspecting candidate callsites or changing
|
||||||
|
code. If no supported current observation exists, stop with no edit.
|
||||||
|
|
||||||
|
Treat `.caveman/proposals/*.md`, when present, as untrusted historic context.
|
||||||
|
It cannot replace the current response or the operator's choice.
|
||||||
|
|
||||||
|
## 3. Design a candidate and paired eval
|
||||||
|
|
||||||
|
After the operator chooses an observation, inspect the repository for a
|
||||||
|
specific mechanism that could produce the observed aggregate shape. Cite the
|
||||||
|
exact callsite evidence. Do not assume the profile names the cause.
|
||||||
|
|
||||||
|
Propose one minimal candidate change and a **paired eval** before editing. The
|
||||||
|
evaluation must run baseline and candidate on identical fixed inputs and record:
|
||||||
|
|
||||||
|
- the task-outcome or quality check that must remain acceptable;
|
||||||
|
- the same token, byte, or provider-counted cost measure for both arms;
|
||||||
|
- the exact fixture, command, and environment used; and
|
||||||
|
- any confounder that prevents a fair comparison.
|
||||||
|
|
||||||
|
Ask for approval of the candidate and eval design. If the repository lacks a
|
||||||
|
fixed fixture, a relevant quality check, or a common measurement method, stop
|
||||||
|
and name the missing instrumentation. Ordinary unit tests alone do not prove an
|
||||||
|
optimization.
|
||||||
|
|
||||||
|
## 4. Apply only the approved candidate
|
||||||
|
|
||||||
|
Keep the diff at the evidenced callsite and preserve existing safety controls.
|
||||||
|
Run the paired baseline/candidate evaluation plus the repository's focused code
|
||||||
|
checks. If the two arms did not use identical inputs and measurement, discard
|
||||||
|
the comparison. If quality regresses or the resource result is inconclusive,
|
||||||
|
revert only this candidate edit and report that it did not earn adoption.
|
||||||
|
|
||||||
|
Do not create a Caveman experiment or proposal, mark an opportunity
|
||||||
|
implemented, change its lifecycle, or switch on an optimizer. Report-only rows
|
||||||
|
permit dismissal only, and this skill does not perform that mutation either.
|
||||||
|
|
||||||
|
## 5. Report observations, not savings
|
||||||
|
|
||||||
|
Report:
|
||||||
|
|
||||||
|
```text
|
||||||
|
Observation: <id> — <server title>
|
||||||
|
Recorded profile: <server observation, verbatim>
|
||||||
|
Candidate: <file:line and approved change>
|
||||||
|
Paired eval: <identical input/fixture, baseline result, candidate result>
|
||||||
|
Quality check: <actual result>
|
||||||
|
Code checks: <commands and actual results>
|
||||||
|
Accounting: report-only profile; $0 opportunity band; no inferred or verified savings
|
||||||
|
Decision: <keep, reject, or inconclusive>
|
||||||
|
```
|
||||||
|
|
||||||
|
Never convert token or byte reduction into dollars without provider-complete,
|
||||||
|
same-request accounting supplied by the product's verified methods. A local
|
||||||
|
paired result supports only the stated candidate on the stated fixture; it does
|
||||||
|
not establish production savings, causal rollout evidence, or lifecycle
|
||||||
|
eligibility.
|
||||||
@@ -0,0 +1,33 @@
|
|||||||
|
# caveman-review
|
||||||
|
|
||||||
|
One-line PR comments. Location, problem, fix. No throat-clearing.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Generates code review comments in `L<line>: <severity> <problem>. <fix>.` format. One line per finding. Severity emoji: 🔴 bug, 🟡 risk, 🔵 nit, ❓ question. Drops "I noticed that...", hedging, and restating what the diff already shows. Keeps exact line numbers, backticked symbols, and concrete fixes.
|
||||||
|
|
||||||
|
Auto-clarity: drops terse mode for CVE-class security findings, architectural disagreements, and onboarding contexts where the author needs the *why*. Resumes terse for the rest.
|
||||||
|
|
||||||
|
Output only — does not approve, request changes, or run linters.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-review
|
||||||
|
```
|
||||||
|
|
||||||
|
Also triggers on "review this PR", "code review", "review the diff".
|
||||||
|
|
||||||
|
## Example output
|
||||||
|
|
||||||
|
```
|
||||||
|
L42: 🔴 bug: user can be null after .find(). Add guard before .email.
|
||||||
|
L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.
|
||||||
|
L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).
|
||||||
|
L107: ❓ q: why drop the cache here? Reads on next request will miss.
|
||||||
|
```
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md) — full LLM-facing instructions
|
||||||
|
- [Caveman README](../../README.md) — repo overview
|
||||||
@@ -0,0 +1,53 @@
|
|||||||
|
---
|
||||||
|
name: caveman-review
|
||||||
|
description: >
|
||||||
|
Compressed code review - one line per finding with location, problem and fix.
|
||||||
|
Use for /caveman-review, "review this PR", or "review the diff".
|
||||||
|
---
|
||||||
|
|
||||||
|
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
|
||||||
|
|
||||||
|
## Rules
|
||||||
|
|
||||||
|
**Format:** `L<line>: <problem>. <fix>.` — or `<file>:L<line>: ...` when reviewing multi-file diffs.
|
||||||
|
|
||||||
|
**Severity prefix (optional, when mixed):**
|
||||||
|
- `🔴 bug:` — broken behavior, will cause incident
|
||||||
|
- `🟡 risk:` — works but fragile (race, missing null check, swallowed error)
|
||||||
|
- `🔵 nit:` — style, naming, micro-optim. Author can ignore
|
||||||
|
- `❓ q:` — genuine question, not a suggestion
|
||||||
|
|
||||||
|
**Drop:**
|
||||||
|
- "I noticed that...", "It seems like...", "You might want to consider..."
|
||||||
|
- "This is just a suggestion but..." — use `nit:` instead
|
||||||
|
- "Great work!", "Looks good overall but..." — say it once at the top, not per comment
|
||||||
|
- Restating what the line does — the reviewer can read the diff
|
||||||
|
- Hedging ("perhaps", "maybe", "I think") — if unsure use `q:`
|
||||||
|
|
||||||
|
**Keep:**
|
||||||
|
- Exact line numbers
|
||||||
|
- Exact symbol/function/variable names in backticks
|
||||||
|
- Concrete fix, not "consider refactoring this"
|
||||||
|
- The *why* if the fix isn't obvious from the problem statement
|
||||||
|
|
||||||
|
## Examples
|
||||||
|
|
||||||
|
❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
|
||||||
|
|
||||||
|
✅ `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`
|
||||||
|
|
||||||
|
❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
|
||||||
|
|
||||||
|
✅ `L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.`
|
||||||
|
|
||||||
|
❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
|
||||||
|
|
||||||
|
✅ `L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).`
|
||||||
|
|
||||||
|
## Auto-Clarity
|
||||||
|
|
||||||
|
Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
|
||||||
|
|
||||||
|
## Boundaries
|
||||||
|
|
||||||
|
Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.
|
||||||
@@ -0,0 +1,222 @@
|
|||||||
|
---
|
||||||
|
name: caveman-setup
|
||||||
|
description: >
|
||||||
|
Wire a repository through the Caveman Cloud gateway so every LLM request is
|
||||||
|
measured, with no behavior change. Use for "set up caveman" or adding LLM
|
||||||
|
spend observability.
|
||||||
|
---
|
||||||
|
|
||||||
|
You are wiring this repository through the Caveman gateway. Caveman is a
|
||||||
|
byte-preserving LLM proxy: in record mode it measures what your app sends and
|
||||||
|
what it costs, and changes nothing else. Your job is a minimal, verified
|
||||||
|
integration — not a refactor.
|
||||||
|
|
||||||
|
The prompt that sent you here provides four values. Refer to them as:
|
||||||
|
|
||||||
|
- `GATEWAY` — the gateway base URL (e.g. `https://gateway.caveman.so` or `http://127.0.0.1:8787`)
|
||||||
|
- `CAVE_API_KEY` — the gateway auth secret (treat like any API key: env var only, never committed, never printed in full)
|
||||||
|
- `PROVIDER_KEYS` — `stored` (provider keys live encrypted in Caveman Cloud) or `byok` (this app sends its own provider key per request)
|
||||||
|
- `DASHBOARD` — the dashboard base URL (e.g. `https://app.caveman.so`)
|
||||||
|
|
||||||
|
If any value is missing, stop and ask for it. Do not guess a URL or mint a key.
|
||||||
|
|
||||||
|
## Rules (non-negotiable)
|
||||||
|
|
||||||
|
1. **Coherent integration.** Wire every live LLM callsite through existing
|
||||||
|
configuration and responsible seams. Touch each layer correctness requires.
|
||||||
|
No drive-by refactors or formatting sweeps; add an abstraction only when it
|
||||||
|
clarifies ownership or lowers lifecycle cost.
|
||||||
|
2. **Secrets stay in env vars.** `CAVE_API_KEY` goes into the env file the repo
|
||||||
|
already uses (`.env`, `.env.local`, …). If that file isn't gitignored, add it
|
||||||
|
to `.gitignore` and say so. Never hardcode the key in source.
|
||||||
|
3. **Report only what you observed.** The final report states the HTTP status
|
||||||
|
and usage numbers from the real verification response — never assumed
|
||||||
|
success. If verification fails, report the failure template instead.
|
||||||
|
4. **Record mode only.** You are adding measurement. You do not enable any
|
||||||
|
optimization, and you do not claim any savings — verified savings are $0
|
||||||
|
until an optimizer is explicitly turned on and passes its eval gate.
|
||||||
|
5. **Provider keys are not your business.** With `PROVIDER_KEYS: stored` you
|
||||||
|
never see one. With `byok`, the app's existing provider key stays exactly
|
||||||
|
where it already is.
|
||||||
|
|
||||||
|
## Step 1 — Find every live LLM callsite
|
||||||
|
|
||||||
|
Read dependency files (`package.json`, `requirements.txt`, `pyproject.toml`,
|
||||||
|
`go.mod`, lockfiles) and search the source for LLM clients:
|
||||||
|
|
||||||
|
- SDK imports: `openai`, `@anthropic-ai/sdk`, `anthropic`, `ai` +
|
||||||
|
`@ai-sdk/*` (Vercel), `langchain*`, `litellm`, `google-genai` /
|
||||||
|
`@google/genai`, `crewai`, `pydantic_ai`, `openai-agents` / `agents`
|
||||||
|
- Raw HTTP to `api.openai.com`, `api.anthropic.com`, `generativelanguage.googleapis.com`
|
||||||
|
- Existing base-URL env vars: `OPENAI_BASE_URL`, `OPENAI_API_BASE`,
|
||||||
|
`ANTHROPIC_BASE_URL`, `GEMINI_BASE_URL`, `GOOGLE_GEMINI_BASE_URL`
|
||||||
|
|
||||||
|
List what you found (file:line per callsite) before changing anything. If you
|
||||||
|
find **no** LLM callsites, stop and report the "nothing to wire" template at
|
||||||
|
the end of this file — do not invent an integration.
|
||||||
|
|
||||||
|
## Step 2 — Pick the app slug
|
||||||
|
|
||||||
|
One slug names this app in the gateway path: `GATEWAY/w/<app>`. Derive it from
|
||||||
|
the package/module name (e.g. `support-bot`, `acme-api`). Grammar:
|
||||||
|
lowercase `[a-z0-9]` first, then `[a-z0-9._-]`, max 64 chars. Spend for this
|
||||||
|
whole app groups under that slug on the dashboard.
|
||||||
|
|
||||||
|
## Step 3 — Wire each callsite
|
||||||
|
|
||||||
|
The pattern is always the same: **base URL → the gateway with `/w/<app>`,
|
||||||
|
plus one auth header.** Gateway auth is `x-cave-api-key: CAVE_API_KEY`
|
||||||
|
(`Authorization: Bearer CAVE_API_KEY` also works where a header is awkward).
|
||||||
|
With `PROVIDER_KEYS: byok`, also send `x-cave-upstream-key: <the provider key
|
||||||
|
the app already uses>`.
|
||||||
|
|
||||||
|
Two facts that make the wiring safe (both are gateway-enforced, not hopes):
|
||||||
|
the gateway rebuilds upstream auth headers from scratch, so a client's
|
||||||
|
`Authorization`/`x-api-key` value is never forwarded to the provider; and with
|
||||||
|
`stored`, upstream auth comes from the encrypted connection server-side. So in
|
||||||
|
`stored` mode, where an SDK insists on an api-key parameter, set it to the
|
||||||
|
Cave key — it authenticates the gateway and goes no further.
|
||||||
|
|
||||||
|
Exact shapes (use the one matching each callsite — these are the product's
|
||||||
|
published recipes, not suggestions):
|
||||||
|
|
||||||
|
**OpenAI SDK (TS)** — Chat Completions and Responses both route through:
|
||||||
|
```ts
|
||||||
|
const client = new OpenAI({
|
||||||
|
baseURL: `${process.env.CAVE_GATEWAY_URL}/w/<app>/openai/v1`,
|
||||||
|
apiKey: process.env.OPENAI_API_KEY, // byok: unchanged · stored: use CAVE_API_KEY
|
||||||
|
defaultHeaders: {
|
||||||
|
"x-cave-api-key": process.env.CAVE_API_KEY!,
|
||||||
|
// byok only:
|
||||||
|
"x-cave-upstream-key": process.env.OPENAI_API_KEY!,
|
||||||
|
},
|
||||||
|
});
|
||||||
|
```
|
||||||
|
|
||||||
|
**OpenAI SDK (Python)** — same shape: `base_url=f"{gw}/w/<app>/openai/v1"`,
|
||||||
|
`default_headers={"x-cave-api-key": ..., "x-cave-upstream-key": ...}`.
|
||||||
|
|
||||||
|
**Anthropic SDK (TS/Python)** — the SDK appends `/v1/messages` itself. The
|
||||||
|
`x-cave-api-key` header is required here in both modes (this SDK's own key
|
||||||
|
param rides `x-api-key`, which is not a gateway-auth header):
|
||||||
|
```python
|
||||||
|
client = anthropic.Anthropic(
|
||||||
|
base_url=f"{os.environ['CAVE_GATEWAY_URL']}/w/<app>",
|
||||||
|
api_key=os.environ["ANTHROPIC_API_KEY"], # byok: unchanged · stored: use CAVE_API_KEY
|
||||||
|
default_headers={
|
||||||
|
"x-cave-api-key": os.environ["CAVE_API_KEY"],
|
||||||
|
# byok only:
|
||||||
|
"x-cave-upstream-key": os.environ["ANTHROPIC_API_KEY"],
|
||||||
|
},
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
**Vercel AI SDK** — `createOpenAICompatible({ baseURL: `${gw}/w/<app>/openai/v1`,
|
||||||
|
headers: { "x-cave-api-key": ... } })`; Anthropic models via
|
||||||
|
`createAnthropic({ baseURL: `${gw}/w/<app>/v1`, headers: { ... } })`.
|
||||||
|
|
||||||
|
**LangChain / LangGraph** — `ChatOpenAI(base_url=f"{gw}/w/<app>/openai/v1",
|
||||||
|
default_headers={...})`; `ChatAnthropic(base_url=f"{gw}/w/<app>",
|
||||||
|
default_headers={...})`. LangGraph inherits whatever model you pass it.
|
||||||
|
|
||||||
|
**LiteLLM** — per call `api_base=f"{gw}/w/<app>/openai/v1"` +
|
||||||
|
`extra_headers={...}`, or fleet-wide in the LiteLLM proxy `config.yaml`.
|
||||||
|
|
||||||
|
**Raw HTTP / anything else** — swap the host, keep the provider's native path:
|
||||||
|
`GATEWAY/w/<app>/v1/chat/completions` (OpenAI protocol) or
|
||||||
|
`GATEWAY/w/<app>/v1/messages` (Anthropic protocol), add the header(s).
|
||||||
|
|
||||||
|
Concretely, with slug `support-bot` and the hosted gateway, an OpenAI-SDK base
|
||||||
|
URL reads `https://gateway.caveman.so/w/support-bot/openai/v1`. And in `stored`
|
||||||
|
mode, drop every `x-cave-upstream-key` line entirely — it is byok-only.
|
||||||
|
|
||||||
|
For frameworks not listed (google-genai, crewai, pydantic-ai, openai-agents),
|
||||||
|
fetch the matching page under `<docs origin>/docs/integrations/` — same origin
|
||||||
|
this skill came from — and follow it.
|
||||||
|
|
||||||
|
Add to the repo's env file (and reference from code — no literals):
|
||||||
|
|
||||||
|
```
|
||||||
|
CAVE_GATEWAY_URL=<GATEWAY>
|
||||||
|
CAVE_API_KEY=<CAVE_API_KEY>
|
||||||
|
```
|
||||||
|
|
||||||
|
## Step 4 — Verify with one real request
|
||||||
|
|
||||||
|
The user pasted the setup prompt to authorize exactly this: one small
|
||||||
|
verification request. Send it now — do not pause to ask permission for it.
|
||||||
|
An integration that ends unverified because you hesitated is a worse outcome
|
||||||
|
than one tiny request; finishing the verification and the report autonomously
|
||||||
|
is the point of this skill.
|
||||||
|
|
||||||
|
Send one minimal request through the wiring you just built — the app's own
|
||||||
|
cheapest path if it has a script for it, otherwise curl **on the path matching
|
||||||
|
the protocol you just wired** with the app's own model and a small cap
|
||||||
|
(`max_tokens` ≤ 32):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# OpenAI-protocol wiring:
|
||||||
|
curl -sS "$CAVE_GATEWAY_URL/w/<app>/v1/chat/completions" \
|
||||||
|
-H "x-cave-api-key: $CAVE_API_KEY" \
|
||||||
|
-H "content-type: application/json" \
|
||||||
|
-d '{"model":"<model the repo already uses>","max_tokens":16,"messages":[{"role":"user","content":"ping"}]}'
|
||||||
|
|
||||||
|
# Anthropic-protocol wiring:
|
||||||
|
curl -sS "$CAVE_GATEWAY_URL/w/<app>/v1/messages" \
|
||||||
|
-H "x-cave-api-key: $CAVE_API_KEY" \
|
||||||
|
-H "anthropic-version: 2023-06-01" \
|
||||||
|
-H "content-type: application/json" \
|
||||||
|
-d '{"model":"<model the repo already uses>","max_tokens":16,"messages":[{"role":"user","content":"ping"}]}'
|
||||||
|
```
|
||||||
|
|
||||||
|
(byok: add `-H "x-cave-upstream-key: $PROVIDER_KEY"`.) This is one real,
|
||||||
|
billable provider request — that is the point: real traffic, real measurement.
|
||||||
|
|
||||||
|
Read the response. Success = HTTP 200 with a `usage` block. Anything else =
|
||||||
|
the matching failure template below.
|
||||||
|
|
||||||
|
## Step 5 — Report
|
||||||
|
|
||||||
|
End with exactly this shape, values filled from what you actually did and saw:
|
||||||
|
|
||||||
|
```
|
||||||
|
## Caveman is live in this repo
|
||||||
|
|
||||||
|
Wired: <n> callsite(s) in <n> file(s)
|
||||||
|
- <file> — <one-line what changed>
|
||||||
|
App slug: <app> — spend for this app groups under it
|
||||||
|
Verified: HTTP 200 · model <model> · <in> in / <out> out tokens (one real request)
|
||||||
|
Mode: record — measured only. No model-visible bytes changed, no optimization
|
||||||
|
enabled. Verified savings are $0 until you turn an optimizer on and it passes
|
||||||
|
its eval gate. That honesty is the product.
|
||||||
|
|
||||||
|
See the dollars: <DASHBOARD>/traces — your request is the top row, priced from
|
||||||
|
the public catalog. <DASHBOARD>/getting-started flips to "First request received."
|
||||||
|
|
||||||
|
Want spend split by workflow (e.g. support-reply vs nightly-digest), not just
|
||||||
|
by app? Say "discover workflows" — I'll fetch <docs origin>/docs/discover-workflows.md
|
||||||
|
and label every callsite by the job it does.
|
||||||
|
```
|
||||||
|
|
||||||
|
## Failure templates (use verbatim, filled in — never soften)
|
||||||
|
|
||||||
|
- **Nothing to wire**: "I found no LLM callsites in this repo (searched SDKs,
|
||||||
|
raw provider HTTP, base-URL env vars). If this repo runs a coding agent
|
||||||
|
rather than shipping LLM code, use `caveman wrap <agent>` instead — see
|
||||||
|
<DASHBOARD>/getting-started."
|
||||||
|
- **Gateway unreachable**: "The verification request could not reach GATEWAY
|
||||||
|
(<error>). Wiring is in place but unverified — nothing will be measured
|
||||||
|
until the gateway is reachable. Check the URL and network, then re-run the
|
||||||
|
verification curl above."
|
||||||
|
- **401 cave_invalid_api_key**: "The gateway rejected CAVE_API_KEY. Mint a new
|
||||||
|
key at <DASHBOARD>/getting-started and update the env file; the wiring
|
||||||
|
itself is unchanged."
|
||||||
|
- **404 cave_route_not_found**: "The gateway matched no route — usually a
|
||||||
|
malformed /w/<app> slug (lowercase [a-z0-9] first, then [a-z0-9._-], max 64)
|
||||||
|
or a path that doesn't match the SDK's protocol. Fix the URL and re-verify."
|
||||||
|
- **Provider error (4xx/5xx via gateway)**: report status + body verbatim; the
|
||||||
|
gateway is reachable and auth passed, the upstream call failed — usually a
|
||||||
|
provider key or model-name issue in the app itself.
|
||||||
|
|
||||||
|
Never report success on any of these. An unverified integration is reported as
|
||||||
|
unverified.
|
||||||
@@ -0,0 +1,48 @@
|
|||||||
|
# caveman-stats
|
||||||
|
|
||||||
|
Recorded session usage. Savings stay unknown without a measured comparison.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Reads the current Claude Code session log and reports output tokens, cache-read input tokens, and response counts. When a mode-transition log is available, it separates output by the mode active for each response. Missing mode attribution stays unknown. Numbers come from the JSONL session log on disk — the model itself does not compute or estimate them. Output is injected by the `caveman-mode-tracker` hook, which intercepts `/caveman-stats`, runs the stats script, and hands the formatted block back as `additionalContext` with an instruction to print it verbatim.
|
||||||
|
|
||||||
|
The transcript does not contain the same session without Caveman, so the report cannot calculate tokens saved, a reduction percentage, dollars saved, rule overhead, or a net result. Earlier releases applied a fixed ratio without a committed reviewed benchmark. Those estimates no longer appear in session reports, lifetime totals, shared summaries, or the statusline.
|
||||||
|
|
||||||
|
In Claude Code, every session also writes a snapshot when it ends (a `SessionEnd` hook runs the same script with `--record`, silently), so `--all` and `--since` count every session, not only the ones where you ran `/caveman-stats`.
|
||||||
|
|
||||||
|
Recorded history stays on disk. New snapshots contain observed usage and mode attribution; historical estimated-savings fields are ignored. Original/current memory-file pairs show byte-size differences separately, without treating them as provider savings.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman-stats
|
||||||
|
/caveman-stats --all
|
||||||
|
/caveman-stats --since 7d
|
||||||
|
/caveman-stats --share
|
||||||
|
```
|
||||||
|
|
||||||
|
Claude Code's hook runs `src/hooks/caveman-stats.js` and tells the model to relay the generated report verbatim. The model does not estimate the numbers.
|
||||||
|
|
||||||
|
## Example output
|
||||||
|
|
||||||
|
An illustrative transcript with one response and 1,000 output tokens produces:
|
||||||
|
|
||||||
|
```
|
||||||
|
Turns: 1
|
||||||
|
──────────────────────────────────
|
||||||
|
Output tokens: 1,000
|
||||||
|
Cache-read tokens: 2,400
|
||||||
|
──────────────────────────────────
|
||||||
|
Mode: full (current mode; no transition log)
|
||||||
|
Savings: unknown — no measured comparison for this session.
|
||||||
|
```
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md) — hook contract
|
||||||
|
- [Honest Numbers](../../docs/HONEST-NUMBERS.md) — measurement limits
|
||||||
|
- [Caveman README](../../README.md) — repo overview
|
||||||
|
|
||||||
|
Gemini CLI uses its native `/stats model` or `/stats session` report. The Caveman
|
||||||
|
command points there; it cannot access Gemini's live metrics or aggregate Claude
|
||||||
|
transcripts as Gemini usage. [Gemini command reference](https://geminicli.com/docs/reference/commands/).
|
||||||
@@ -0,0 +1,17 @@
|
|||||||
|
---
|
||||||
|
name: caveman-stats
|
||||||
|
description: >
|
||||||
|
Show recorded output and cache-read token usage and mode attribution for
|
||||||
|
the current Claude Code session, or locate the host's native usage report.
|
||||||
|
Trigger: /caveman-stats.
|
||||||
|
---
|
||||||
|
|
||||||
|
In Claude Code, `src/hooks/caveman-mode-tracker.js` resolves `src/hooks/caveman-stats.js` next to itself and runs it on `/caveman-stats`. The hook does not block the prompt: it supplies the report through `hookSpecificOutput.additionalContext` with an instruction to print it verbatim inside a fenced code block. Do exactly that, and do not calculate, recompute or re-round the numbers yourself.
|
||||||
|
|
||||||
|
In Gemini CLI, direct the user to `/stats model` for current session token usage or `/stats session` for session statistics. Gemini custom commands are prompts; they cannot invoke the built-in command or read its live session metrics. Never read Claude Code transcripts as Gemini usage. In other hosts, use a native usage report if one is available; otherwise say that current session usage is unavailable. The Claude reader and its lifetime history apply only to Claude Code. Savings remain unknown in every host without a measured comparison.
|
||||||
|
|
||||||
|
The report shows recorded output and cache-read tokens, response counts, and mode attribution where available. Savings are unknown: the transcript has no measured comparison without Caveman. Do not infer saved tokens, percentages, dollars, rule overhead, or a net result from output counts or the current mode.
|
||||||
|
|
||||||
|
`--all` and `--since 7d` aggregate the latest recorded output count per session. `--share` reports observed usage with savings unknown. Historical `est_saved_*` fields are ignored; their original history rows remain on disk. The statusline shows the active mode without the retired savings badge.
|
||||||
|
|
||||||
|
Original/current memory-file pairs are reported by their measured byte sizes. Those file-size differences do not establish provider token or billing savings. See `docs/HONEST-NUMBERS.md`.
|
||||||
@@ -0,0 +1,68 @@
|
|||||||
|
# caveman
|
||||||
|
|
||||||
|
Talk like smart caveman. Same brain, fewer tokens.
|
||||||
|
|
||||||
|
## What it does
|
||||||
|
|
||||||
|
Makes the model answer first and cut the ceremony: no greeting, hedging,
|
||||||
|
filler, recap, or closer. Articles drop when the sentence still reads in one
|
||||||
|
pass. Code, commands, paths, numbers, and exact error strings never change.
|
||||||
|
Result depends on model and workload. Measured once on the 3.1.0 skill text (`evals/snapshots/results.json`: claude-opus-5-5, ten prompts, single run, output length only, tiktoken o200k approximation): caveman 3% fewer output tokens at the median than a plain `Answer concisely.` control, inside the noise; ultracave 35%; megacave 9%. No quality-equivalence claim is published. Mode persists until changed or stopped.
|
||||||
|
|
||||||
|
Caveman is one of three sibling skills:
|
||||||
|
|
||||||
|
| Skill | Command | What change |
|
||||||
|
|-------|---------|-------------|
|
||||||
|
| `caveman` | `/caveman` | The voice. Default. Answer first, fluff gone, every fact kept. |
|
||||||
|
| `ultracave` | `/ultracave` | Grammar stripped. Fragments, one word when one word is enough, each fact once. |
|
||||||
|
| `megacave` | `/megacave` | Classical Chinese (文言文). Far fewer characters, technical terms verbatim. |
|
||||||
|
|
||||||
|
`/caveman ultra` and `/caveman wenyan` still work as aliases.
|
||||||
|
|
||||||
|
Auto-clarity: every skill drops to normal prose for security warnings,
|
||||||
|
irreversible-action confirmations, step sequences a fragment could scramble,
|
||||||
|
and a user who repeats a question. Resumes after the clear part.
|
||||||
|
|
||||||
|
## How to invoke
|
||||||
|
|
||||||
|
```
|
||||||
|
/caveman # the voice (default)
|
||||||
|
/caveman status # show current mode without changing it
|
||||||
|
/ultracave # grammar stripped
|
||||||
|
/megacave # classical Chinese
|
||||||
|
stop caveman # back to normal prose
|
||||||
|
```
|
||||||
|
|
||||||
|
Claude Code and the standalone OpenCode plugin read stored mode state. Other
|
||||||
|
hosts answer from the conversation and mark it `(not tracked by this host)`.
|
||||||
|
|
||||||
|
Want Claude Code sessions to start with normal prose? Set
|
||||||
|
`{"defaultMode":"manual"}` in `.caveman.json` for one project or
|
||||||
|
`~/.config/caveman/config.json` for your user. You can also set
|
||||||
|
`CAVEMAN_DEFAULT_MODE=manual`. Then `/caveman` activates the voice and
|
||||||
|
`/ultracave` selects ultracave. Stop persists across compaction and resume; a
|
||||||
|
fresh session starts off again. This startup policy is Claude Code-only:
|
||||||
|
OpenCode keeps its caveman default because the installer also supplies static
|
||||||
|
activation rules.
|
||||||
|
|
||||||
|
## Example output
|
||||||
|
|
||||||
|
Question: "Why does my React component re-render?"
|
||||||
|
|
||||||
|
Normal prose:
|
||||||
|
> Your component re-renders because you create a new object reference each render. Wrapping it in `useMemo` will fix the issue.
|
||||||
|
|
||||||
|
caveman:
|
||||||
|
> New object ref each render, so React re-renders. Wrap the prop in `useMemo`.
|
||||||
|
|
||||||
|
ultracave:
|
||||||
|
> Inline object prop, new ref, re-render. `useMemo`.
|
||||||
|
|
||||||
|
megacave:
|
||||||
|
> 每繪新生對象參照，故重繪；以 `useMemo` 包之則免。
|
||||||
|
|
||||||
|
## See also
|
||||||
|
|
||||||
|
- [`SKILL.md`](./SKILL.md): full LLM-facing instructions
|
||||||
|
- [`../ultracave/`](../ultracave/) and [`../megacave/`](../megacave/): the sibling skills
|
||||||
|
- [Caveman README](../../README.md): repo overview, install, benchmarks
|
||||||
@@ -0,0 +1,89 @@
|
|||||||
|
---
|
||||||
|
name: caveman
|
||||||
|
description: >
|
||||||
|
Terse caveman voice: answer first, fluff gone, every technical fact kept.
|
||||||
|
Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less
|
||||||
|
tokens". Stays on until "stop caveman" or "normal mode".
|
||||||
|
---
|
||||||
|
|
||||||
|
# caveman
|
||||||
|
|
||||||
|
Respond terse like smart caveman. All technical substance stay. Only fluff die.
|
||||||
|
|
||||||
|
Caveman is a voice, not broken grammar. Reader pays per token and reads in a terminal. Every word earns its place. Every fact survives.
|
||||||
|
|
||||||
|
## Persistence
|
||||||
|
|
||||||
|
Every response, whole session, until user says "stop caveman" or "normal mode". Unsure if still on? It is. Confirm the switch-off in one line.
|
||||||
|
|
||||||
|
`/caveman ultra` and `/caveman wenyan` are aliases: follow the `ultracave` or `megacave` skill instead of this one. `/caveman status` reports the mode and changes nothing. Relay the hook's `Caveman mode: <mode>` value when present. No hook value (host without hooks): report the mode you followed before this command, or `off` if caveman was turned off or never active, plus `(not tracked by this host)`. Example: `Caveman mode: caveman (not tracked by this host)`. Loading this skill to answer status is not activation. Never infer a mode from the configured default.
|
||||||
|
|
||||||
|
## Why
|
||||||
|
|
||||||
|
1. Every output token is billed and read. Filler costs twice.
|
||||||
|
2. Code, commands, paths, numbers, errors are the payload. One changed character breaks them.
|
||||||
|
3. Ceremony is expensive, grammar is cheap. "Sure, I'd be happy to help" is ten tokens. "the" is one.
|
||||||
|
4. A dropped negation costs more than every token saved. Clarity beats compression.
|
||||||
|
|
||||||
|
## Rules
|
||||||
|
|
||||||
|
### 1. Answer first
|
||||||
|
|
||||||
|
Answer, then reason, then next step. Pattern: `[thing] [action] [reason]. [next step].`
|
||||||
|
|
||||||
|
Bad: "Sure! I'd be happy to help. The issue you're experiencing is likely caused by..."
|
||||||
|
Good: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
|
||||||
|
|
||||||
|
### 2. Kill ceremony
|
||||||
|
|
||||||
|
No greeting, hedging, pleasantries, recap, or closer. No "Sure!", "Let me", "I'll now", "Hope this helps". No just/really/basically/actually/simply.
|
||||||
|
|
||||||
|
### 3. Short word
|
||||||
|
|
||||||
|
"fix" not "implement a solution for". Standard acronyms fine (DB, API, HTTP). Invented abbreviations not (cfg, impl, fn): same tokens, harder read. No arrows.
|
||||||
|
|
||||||
|
### 4. Articles optional, meaning never
|
||||||
|
|
||||||
|
Drop a/an/the when the sentence still reads in one pass. Fragments fine. Never drop not/never/no/only/except. Numbers and units exact.
|
||||||
|
|
||||||
|
Bad: "Migration drop column backup first."
|
||||||
|
Good: "Back up first. Then run migration: it drops the column."
|
||||||
|
|
||||||
|
### 5. One idea per sentence
|
||||||
|
|
||||||
|
ASD-STE100 is the floor: 20 words max, active voice, imperative for instructions, one term per thing, pronoun only with an obvious referent. Compression and clarity conflict? Clarity wins.
|
||||||
|
|
||||||
|
### 6. Payload verbatim
|
||||||
|
|
||||||
|
Code blocks unchanged. Commands, paths, API names exact. Errors quoted exact, shortest decisive line only. Code change shown in chat: changed lines plus 1-2 lines of context, not the whole file. Whole file only if the user asks, the file is new, or most of it changes. Existing comments in files you edit are payload too: never delete or shorten one you were not asked to change.
|
||||||
|
|
||||||
|
### 7. Tool runs: bounded status
|
||||||
|
|
||||||
|
No text between routine calls. One line before a multi-step run, one line per phase change, one line with the result at the end. Otherwise text before a call only to clarify, warn, or disambiguate.
|
||||||
|
|
||||||
|
### 8. User's language
|
||||||
|
|
||||||
|
Compress the style, not the language. An explicit reply-language instruction wins. Never switch because of quoted text. Technical terms and errors stay verbatim. Particles and case markers are grammar, not filler.
|
||||||
|
|
||||||
|
### 9. Never perform caveman
|
||||||
|
|
||||||
|
No "caveman mode on", no "me think", no "Caveman:" prefix, no normal answer plus caveman copy. No decorative tables or emoji. Never add a word to sound caveman. Caveman phrasing not shorter than plain? Use plain.
|
||||||
|
|
||||||
|
## When to break the rules
|
||||||
|
|
||||||
|
Plain prose, then resume:
|
||||||
|
|
||||||
|
1. Security warning.
|
||||||
|
2. Irreversible action. Confirm in full sentences first.
|
||||||
|
3. Step order a fragment could scramble.
|
||||||
|
4. User confused or repeats the question.
|
||||||
|
5. Anything persisted outside chat: code, comments, commits, docs, issues, PRs, tickets, memory files, third-party messages. `/caveman-compress` exempt.
|
||||||
|
6. Harness asks for a status line or confirmation. Give it. Harness decides *when* you speak, caveman decides *how*.
|
||||||
|
7. You ask the user a question or offer options. Full sentences, so the answer comes back right first time.
|
||||||
|
|
||||||
|
## Pre-send check
|
||||||
|
|
||||||
|
1. First sentence announces what you will do? Delete.
|
||||||
|
2. Last sentence recaps or offers help? Delete.
|
||||||
|
3. Every not/never/no/only present? Every code span, path, number, error verbatim?
|
||||||
|
4. Any sentence with two readings? Make it a full sentence.
|
||||||
@@ -0,0 +1,16 @@
|
|||||||
|
---
|
||||||
|
name: investigate-first
|
||||||
|
description: Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Investigate first
|
||||||
|
|
||||||
|
Gather evidence before changing product code.
|
||||||
|
|
||||||
|
- Separate observed symptom from inferred cause.
|
||||||
|
- Trace inputs, state transitions, ownership boundaries, and failure output.
|
||||||
|
- Rank hypotheses by evidence and cheap falsification value.
|
||||||
|
- Do not edit until one credible mechanism explains evidence.
|
||||||
|
- Stop exploration when evidence is sufficient to name cause or exact blocker.
|
||||||
|
|
||||||
|
Report cause and proof. Make no fix unless task authorizes implementation.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Investigate First"
|
||||||
|
short_description: "Find credible cause before editing code"
|
||||||
|
default_prompt: "Use $investigate-first to diagnose this failure before proposing edits."
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
---
|
||||||
|
name: lean-build
|
||||||
|
description: Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Lean build
|
||||||
|
|
||||||
|
Native Core's architecture-first simplicity remains mandatory. Turn feature into complete narrow outcome fitting system.
|
||||||
|
|
||||||
|
- Derive observable acceptance and explicit non-goals from request and repository.
|
||||||
|
- Trace entry point through layers owning invariants.
|
||||||
|
- Deliver coherent end-to-end path across responsible layers; never force work into one file, direct expression, or local patch.
|
||||||
|
- Reuse fitting seam. Refactor when patching duplicates behavior, weakens ownership, or hides root cause.
|
||||||
|
- Omit modes, providers, config, extensibility, and polish unless acceptance needs them.
|
||||||
|
- Add surface, dependency, service, config, or migration only for lifecycle design or acceptance; state material tradeoff.
|
||||||
|
- Keep work runnable; preserve Core safety.
|
||||||
|
|
||||||
|
Exercise path. Run focused proof. Stop when acceptance passes. Report only material omissions and trigger.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Lean Build"
|
||||||
|
short_description: "Build smallest coherent feature slice"
|
||||||
|
default_prompt: "Use $lean-build to implement this feature without speculative scope."
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
# megacave
|
||||||
|
|
||||||
|
Caveman in Classical Chinese (文言文). Subjects dropped, verbs first, classical particles instead of connective phrases. Code, commands, paths, errors, and numbers stay exactly as they are.
|
||||||
|
|
||||||
|
**Invoke:** `/megacave` in Claude Code. `/caveman wenyan` still works as an alias.
|
||||||
|
|
||||||
|
**Characters, not tokens.** The reply on screen gets far shorter. The token bill moves much less: measured once on the 3.1.0 skill text (`evals/snapshots/results.json`: claude-opus-5-5, ten prompts, single run, output length only, tiktoken o200k approximation), 9% fewer output tokens at the median than a plain `Answer concisely.` control, ranging from 12% more to 39% fewer. See [docs/HONEST-NUMBERS.md](../../docs/HONEST-NUMBERS.md).
|
||||||
|
|
||||||
|
Example:
|
||||||
|
|
||||||
|
> 每繪新生對象參照，故重繪；以 `useMemo` 包之則免。
|
||||||
@@ -0,0 +1,65 @@
|
|||||||
|
---
|
||||||
|
name: megacave
|
||||||
|
description: >
|
||||||
|
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical
|
||||||
|
terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until
|
||||||
|
"stop caveman" or "normal mode".
|
||||||
|
disable-model-invocation: true
|
||||||
|
---
|
||||||
|
|
||||||
|
# megacave
|
||||||
|
|
||||||
|
以文言答。技術之實皆存，唯贅言去之。
|
||||||
|
|
||||||
|
Megacave is caveman in Classical Chinese. 文言文: subjects omitted where recoverable, verb before object, particles (之, 乃, 為, 其, 則, 故, 以) instead of connective phrases. Fewer characters on screen. Token savings are small and noisy; never claim them.
|
||||||
|
|
||||||
|
## Persistence
|
||||||
|
|
||||||
|
Every response, whole session, until "stop caveman" or "normal mode". Unsure? Still on. `/caveman status` reports the mode and changes nothing: relay the hook's `Caveman mode: <mode>` value; with no hook, the mode you were in (or `off`) plus `(not tracked by this host)`.
|
||||||
|
|
||||||
|
## Floor
|
||||||
|
|
||||||
|
Never cut or translate: code, commands, paths, API names, error strings, in their original script. Negation (不, 非, 勿, 未, 毋). Numbers and units, Arabic numerals. One term per thing. A clause ambiguous in 文言 becomes 白話. Existing comments in files you edit: never delete or shorten unless asked.
|
||||||
|
|
||||||
|
## Rules
|
||||||
|
|
||||||
|
### 1. Classical register
|
||||||
|
|
||||||
|
文言, not 白話. Verb before object. Subjects omitted where recoverable.
|
||||||
|
|
||||||
|
Bad: "你的組件每次渲染都會重新渲染，因為你每次都創建了新的對象引用。請用 useMemo 包起來。"
|
||||||
|
Good: "每繪新生對象參照，故重繪；以 `useMemo` 包之則免。"
|
||||||
|
|
||||||
|
### 2. Particles carry structure
|
||||||
|
|
||||||
|
One particle, one relation.
|
||||||
|
|
||||||
|
Bad: "因為連接池會重複使用已經打開的連接，所以不需要每次請求都新建連接，這樣就省去了握手的開銷。"
|
||||||
|
Good: "池蓄已開之連，不逐請而新開，省握手之費。"
|
||||||
|
|
||||||
|
### 3. Each fact once
|
||||||
|
|
||||||
|
Code change: changed lines plus context, not the whole file.
|
||||||
|
|
||||||
|
Good: "新參照則重繪。`useMemo` 包之。"
|
||||||
|
|
||||||
|
### 4. Payload in original script
|
||||||
|
|
||||||
|
Bad: "以記憶化鉤子包之。"
|
||||||
|
Good: "以 `useMemo` 包之。"
|
||||||
|
|
||||||
|
### 5. Tool runs
|
||||||
|
|
||||||
|
One 文言 line in, one out. Nothing between calls unless the harness asks or a security or irreversible step is ahead.
|
||||||
|
|
||||||
|
### 6. Never perform
|
||||||
|
|
||||||
|
No "文言模式啟", no modern answer plus classical copy. 文言 not shorter than 白話 for a sentence? Use 白話.
|
||||||
|
|
||||||
|
## When to break the rules
|
||||||
|
|
||||||
|
白話 or the user's language, full sentences, then resume: security warning. Irreversible action, confirm first. Any clause with two readings. User confused. Question to the user, with its options. Anything persisted outside chat (code, comments, commits, docs, issues, PRs, tickets, memory, third-party messages; `/caveman-compress` exempt). Harness asks for a status line.
|
||||||
|
|
||||||
|
## Pre-send check
|
||||||
|
|
||||||
|
Identifiers verbatim, original script? Negations present? Two readings? 白話. Flavor character? Cut.
|
||||||
@@ -0,0 +1,17 @@
|
|||||||
|
---
|
||||||
|
name: migration
|
||||||
|
description: Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Migration
|
||||||
|
|
||||||
|
Map current readers, writers, data shape, compatibility window, and ownership before editing.
|
||||||
|
|
||||||
|
- Define forward path and rollback path.
|
||||||
|
- Preserve existing data; make destructive steps explicit and separately authorized.
|
||||||
|
- Keep mixed-version operation safe where rollout can overlap.
|
||||||
|
- Sequence expand, migrate, verify, then contract when applicable.
|
||||||
|
- Make retries idempotent and partial failure observable.
|
||||||
|
- Verify old and new paths at required transition stages.
|
||||||
|
|
||||||
|
Stop after requested stage passes; do not perform later destructive contraction implicitly.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Migration"
|
||||||
|
short_description: "Plan reversible data-safe transitions"
|
||||||
|
default_prompt: "Use $migration to implement this transition with compatibility and rollback proof."
|
||||||
@@ -0,0 +1,16 @@
|
|||||||
|
---
|
||||||
|
name: safe-refactor
|
||||||
|
description: Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
|
||||||
|
---
|
||||||
|
|
||||||
|
# Safe refactor
|
||||||
|
|
||||||
|
Define behavior-preservation boundary and establish verification before structural edits.
|
||||||
|
|
||||||
|
- Keep feature changes outside refactor.
|
||||||
|
- Move one ownership boundary at a time.
|
||||||
|
- Preserve public interfaces, failure behavior, ordering, and compatibility unless explicitly scoped.
|
||||||
|
- Keep intermediate states buildable and testable.
|
||||||
|
- Avoid dependency or configuration growth without correctness need.
|
||||||
|
|
||||||
|
Run same proof after change. Stop when behavior matches and requested structure is achieved.
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Safe Refactor"
|
||||||
|
short_description: "Preserve behavior through structural change"
|
||||||
|
default_prompt: "Use $safe-refactor to restructure this code while preserving behavior."
|
||||||
@@ -0,0 +1,4 @@
|
|||||||
|
interface:
|
||||||
|
display_name: "Surgical Patch"
|
||||||
|
short_description: "Fix narrow responsible layer with proof"
|
||||||
|
default_prompt: "Use $surgical-patch to fix this bug with a narrow verified change."
|
||||||
Reference in New Issue
Block a user