メニュー
Use when the user wants compressed agent output, types /caveman, asks to talk like caveman, requests shorter responses, or asks to cut output tokens.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when the user wants the laziest solution that actually works — types /ponytail, says "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Supports intensity levels lite, full, ultra (default). Pairs with caveman, which compresses prose, not code.
Use when the user wants a whole-repo audit for over-engineering — says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", or invokes /ponytail-audit. Like ponytail-review but scans the entire tree, not a diff. One-shot report, applies no fixes. Gated by the ponytail audit_ponytail component.
Use when the user wants to harvest every `ponytail:` comment in the codebase into a tracked debt ledger — says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing. Gated by the ponytail debt_ponytail component.
Use when the user asks how ponytail mode works, what intensity levels exist, what the slash commands are, how to toggle it, or wants a quick-reference card before turning the mode on. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
Use when the user wants a code review focused exclusively on over-engineering — says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness/security review; this one only hunts complexity in the current diff. Gated by the ponytail review_ponytail component.
Use when navigating an unfamiliar codebase, tracing how code connects (callers, dependencies, the blast radius of a change), or whenever the repo ships a graphify-out/graph.json knowledge graph. Query the graph before grepping/reading raw source for orientation.
| name | caveman |
| description | Use when the user wants compressed agent output, types /caveman, asks to talk like caveman, requests shorter responses, or asks to cut output tokens. |
| license | MIT |
| metadata | {"author":"ai-playbook (ported from JuliusBrussee/caveman, MIT)","version":"1.0"} |
Compress every reply ~65-75% while keeping full technical accuracy. Brain still big. Mouth small.
User intent triggers (any of):
/caveman or /caveman lite|full|ultra<!-- BEGIN auto-managed: caveman/ruleset:<mode> --> present — auto-active from message one[thing] [action] [reason]. [next step].Drop filler and hedging only. Keep articles. Keep full sentences. Same length but cleaner — about 20-30% reduction. Use when the reader wants tighter prose without telegraphic style.
Drop articles. Fragments OK. Short synonyms. Technical terms exact. Code unchanged. Pattern: [thing] [action] [reason]. [next step]. Default mode — about 65% output reduction.
Drop articles. Abbreviate prose words: DB, auth, cfg, env, repo, fn, ref, ptr, ctx, msg, req, res. Use arrows for causality: inline obj → new ref → re-render. Preserve code symbols and function names byte-for-byte. About 80% output reduction.
Drop caveman mode and use normal prose when:
rm -rf, git push --force, drop database, force-merge, etc.Resume caveman mode on the next turn.
caveman-commit or caveman-review skills.Active every response until the user says "stop caveman", "normal mode", "be verbose", or types /caveman off. Reinforcement comes from the caveman-reinforce paired rule (per-turn nudge) and from the marker block in the consumer's AGENTS.md.