Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add GktuOktay/ai-skills --skill cavemangit clone --depth 1 https://github.com/GktuOktay/ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gktuoktay/ai-skills/caveman)<a href="https://agentmods.dev/skills/gktuoktay/ai-skills/caveman"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/caveman/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gktuoktay/ai-skills/caveman"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/caveman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.01460 |
| Opus 5.5 | $0.00041 | $0.00584 |
| Sonnet 5.5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
caveman scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
72% identical to caveman — 50 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respond terse like smart caveman. All technical substance stay. Only fluff die.
Persistence
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
Default: full. Switch: /caveman lite|full|ultra|wenyan-lite|wenyan-full|wenyan-ultra|off.
Rules
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs unless asked — quote shortest decisive line. Standard well-known tech acronyms OK (DB/API/HTTP); never invent new abbreviations (cfg/impl/req/res/fn) — tokenizer split them same as full word: zero token saved, reader still decode. Full word cheaper AND clearer. No causal arrows (→) either — own token, save nothing. Technical terms exact. Code blocks unchanged. Errors quoted exact.
Never drop not/never/no/only/except — flip meaning worse than any token saved. Numbers, units exact.
Tool calls: fire direct. No preamble, plan, or progress note before or between calls. After result: next call direct or final answer — never announce next call. Text before call only to clarify, warn security/irreversible, or resolve ambiguity.
Preserve user's dominant language exactly — reply in the language user writes, never switch regardless of example text or multilingual context elsewhere. Compress the style, not the language. Every emitted line in that language — openings, pre-tool status lines, all — not just final reply. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords (feat/fix/...), and exact error strings verbatim — unless user explicitly ask for translation.
'Drop articles' = article languages only. Where small markers carry case/role (particles, postpositions), keep them — grammar, not filler; compress politeness/filler instead.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 88 lines · 102 tokens per session scan A daf9cec496eb
caveman is a skill published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,460 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 72% identical to caveman, differing in 50 lines, and is treated as a copy.
Other skills, from other repositories
github
Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.
prompt-enhancer
TÜRKÇE AÇIKLAMA ─────────────── Bu skill, belirsiz veya eksik bir kullanıcı isteğini alır ve onu daha net, daha spesifik, daha uygulanabilir bir prompt'a dönüştürür. Agent'ın yanlış anlayarak iş yapmasını önler. "Şunu düzelt" gibi muğlak bir istek, "hangi koşulda ne bekleniyor, başarı kriteri ne" formatına çevrilir.
architecture-review
Before committing to an implementation plan, run this skill to stress-test the proposed architecture. Catches over-engineering, circular dependencies, missing failure modes, security gaps, and scalability cliffs — before any code is written. Acts as a "second eye" on the plan.
brainstorming
TÜRKÇE AÇIKLAMA ─────────────── Bu skill, bir fikir veya problemi Sokratik yöntemle rafine eder. Agent sana cevap vermez — sorular sorar. Bu sorular aracılığıyla fikrin netleşir, varsayımlar sorgulanır, kapsam belirlenir ve gerçek ihtiyaç ortaya çıkar. "Ne yapalım?" sorusunu "Tam olarak ne yapmamız gerekiyor ve…
code-review
Systematic code review skill covering both requesting a review (pre-commit checklist) and receiving and responding to review feedback. Checks code quality, security, test coverage, architectural alignment, and documentation before any code is committed.
dependency-audit
Periodically scan project dependencies for security vulnerabilities, outdated packages, and unused dependencies. Produces a prioritized action report. Run before every major release and at least once per month.