caveman is a skill and proxy for coding agents that shortens unnecessary explanatory prose so agents use fewer tokens while leaving code, commands, paths, and error messages unchanged. It is for people using coding agents who want terse responses and lower token use, including with Claude-based workflows. The catalogue entries contain its skills, commands, agents, instructions, and plugins.
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.
git clone --depth 1 https://github.com/JuliusBrussee/cavemanWrote 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/commands/juliusbrussee/caveman/caveman-commit)<a href="https://agentmods.dev/commands/juliusbrussee/caveman/caveman-commit"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman/caveman-commit/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/commands/juliusbrussee/caveman/caveman-commit"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman/caveman-commit.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 | $0.00011 | $0.00078 |
| Opus 5.5 | $0.00004 | $0.00031 |
| Sonnet 5.5 | $0.00002 | $0.00016 |
| Haiku 4.5 | $0.00001 | $0.00008 |
Grade A, and why
caveman-commit 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.
What it actually says
Generate a commit message for the current staged changes.
Conventional Commits format. Subject line ≤50 chars, imperative, lowercase after the type. No period on subject. Body only when the "why" isn't obvious from the subject — explain why over what. Drop filler, hedging, padding.
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 · 9 lines · 11 tokens per session scan A 91c95a462a82
caveman-commit is a command published in the GitHub repository JuliusBrussee/caveman (112,527 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 78 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
t00-git
A Git assistant that explains version-control commands and guides work with commits, branches, merges, pull requests, and conflicts. Git records code changes so developers can review, restore, and share versions.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
genshijin-commit
A command that writes a commit message for changes already placed in Git's staging area. It follows the repository's existing language and uses a short imperative subject without AI attribution.
quick-commit
A quick Git command for committing and pushing a small code change. Git is the tool that records code versions and sends them to a shared repository.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.