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 Chemaclass/agnostic-ai --skill cavemangit clone --depth 1 https://github.com/Chemaclass/agnostic-aiWrote 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/chemaclass/agnostic-ai/caveman)<a href="https://agentmods.dev/skills/chemaclass/agnostic-ai/caveman"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/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/chemaclass/agnostic-ai/caveman"><img src="https://agentmods.dev/badge/skills/chemaclass/agnostic-ai/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 | $0.00062 | $0.01158 |
| Opus 5.5 | $0.00025 | $0.00463 |
| Sonnet 5.5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- Every output token is billed and read. Filler costs twice.
- Code, commands, paths, numbers, errors are the payload. One changed character breaks them.
- Ceremony is expensive, grammar is cheap. "Sure, I'd be happy to help" is ten tokens. "the" is one.
- 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.
What ships with it
5 files 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.
- 5d ago First seen · 90 lines · 62 tokens per session scan A 415d43518f2b
caveman is a skill published in the GitHub repository Chemaclass/agnostic-ai (25 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,158 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
tldr
Verdict-first communication mode. Cuts token usage 60-75% by enforcing TLDR rules (1-sentence default, 3-word target, shape dispatch) while preserving full technical accuracy and truth priority. Supports levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "tldr mode", "talk…
tldr-help
Quick-reference card for all tldr modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /tldr-help, "tldr help", "what TLDR commands", "how do I use TLDR".
tldr-update
Update TLDR from GitHub and refresh installed agent hooks, skills, MCP, and rules. Triggers on /tldr-update, "tldr update", "update TLDR", or when the user asks to upgrade the TLDR install. Run via Bash: tldr update or node /bin/install.js update.
usually
Prompt Pocket — remembers your most-used prompts and lets you pick one to run instantly. Auto-records prompts you repeat >= 7 times across agent sessions, plus manual add/delete/edit/find. Pick-to-run and manual management work on every host; auto-scan covers Claude Code, Codex and OpenCode sessions. Use when the user…
audit
General-purpose workspace maintenance pass. Cross-cutting enforcement of multiple core values (One canonical home / Use-driven evolution) and rules (R1 capacity backstop / R3 source-trail integrity + citation backstop). Every action respects R4 T1-T2 boundary procedurally. 7-class issue scan + journal archival (>3…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.