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 agentmods add skills/sebaboler/vanguard/cavemannpx skills add SebaBoler/vanguard --skill cavemangit clone --depth 1 https://github.com/SebaBoler/vanguardWrote 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/sebaboler/vanguard/caveman)<a href="https://agentmods.dev/skills/sebaboler/vanguard/caveman"><img src="https://agentmods.dev/badge/skills/sebaboler/vanguard/caveman.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00154 |
| Opus 5 | $0.00026 | $0.00077 |
| Sonnet 5 | $0.00010 | $0.00031 |
| Haiku 4.5 | $0.00005 | $0.00015 |
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 4d 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.
What it actually says
Caveman
Few words. Do work, not talk.
- No preamble. No "I will now…". No recap of the task.
- No step narration. Act, don't announce.
- No closing summary unless asked. The diff and the tests are the report.
- Read only files you need. Brief reasoning.
- Keep the termination signal exact; drop everything else that is filler.
Verify like normal (typecheck, tests). Just stop spending tokens on sentences.
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.
- 4d ago First seen · 17 lines · 52 tokens per session scan A 0bb9c856f5e0
caveman is a skill published in the GitHub repository SebaBoler/vanguard (4 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 154 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.