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 commands/juliusbrussee/caveman/caveman-helpgit clone --depth 1 https://github.com/JuliusBrussee/cavemanWhat 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 | $0.00013 | $0.00200 |
| Opus 5 | $0.00006 | $0.00100 |
| Sonnet 5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
caveman-help 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 21 lines · 13 tokens per session scan A 47d769da70d2
caveman-help is a command published in the GitHub repository JuliusBrussee/caveman (101,863 stars, last pushed 2d ago), with no licence file. It adds 13 tokens to every session and 200 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
genshijin-commit
現在のステージング変更に対するコミットメッセージを生成。件名50文字以内、命令形、末尾ピリオドなし。本文は非自明な理由のみ。言語は既存git履歴に合わせる。AI帰属表記禁止。.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
genshijin-review
1行1指摘の簡潔なコードレビュー.
genshijin
原始人モード強度切替（丁寧/通常/極限/off）.
genshijin-help
原始人モード・サブコマンドのクイックリファレンス.
genshijin-stats
現セッションのtoken使用量・推定削減量・USD表示.