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 bh-rat/steer --skill commit-messagegit clone --depth 1 https://github.com/bh-rat/steerWrote 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/bh-rat/steer/commit-message)<a href="https://agentmods.dev/skills/bh-rat/steer/commit-message"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/commit-message/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/bh-rat/steer/commit-message"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/commit-message.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 | $0.00020 | $0.00381 |
| Opus 5.5 | $0.00008 | $0.00152 |
| Sonnet 5.5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
commit-message 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
commit-message
Turn whatever is currently staged into one well-formed conventional
commit message the user can apply as-is. The user gets the message text;
you never run git commit yourself.
Steps
- Run:
git diff --cached --statthengit diff --cached. If nothing is staged, say so and stop; never guess from unstaged changes. - Check the diff is atomic (one logical change). If it mixes concerns,
propose how to split it (
git reset -p/ staging hunks) instead of writing a muddled message. - Pick the type and scope. When unsure which type fits, first read
references/conventional-commits.md. - Write the message: imperative subject ≤ 50 chars
(
type(scope): change), blank line, body wrapped at 72 explaining what changed and why, not how. - Present the message in a fenced block, then ask whether to adjust tone or detail.
References
Keep this file lean; put branch-only detail behind pointers so it loads only when that branch is hit:
- When choosing the commit type or handling a breaking change, first read
references/conventional-commits.md.
Gotchas
- Empty staged diff → stop at step 1; do not invent a message.
- Generated/lockfile-only diffs (
uv.lock,package-lock.json) → say the change is mechanical and suggestchore(deps). - Never include ticket numbers or co-author trailers unless the user asks.
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 · 43 lines · 20 tokens per session scan A d3304b50ec44
commit-message is a skill published in the GitHub repository bh-rat/steer (7 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 381 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple…
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
commit-with-reflection
A Git workflow that creates a Chinese-language report about debugging mistakes, investigation steps, fixes, and lessons learned, then includes that report in a commit. Git is a system for tracking changes to code.
setup-pre-commit
A setup for Husky pre-commit checks in a JavaScript or TypeScript repository. A pre-commit hook runs automatically before a Git commit and can format staged files, check types, and run tests.
antfu-create-pr
Create a reviewable GitHub pull request from the current branch with a Conventional Commits title, a concise evidence-based body, and before/after screenshots for UI changes. Use when asked to open, create, publish, or prepare a PR.
commit
Skill "commit" from clacky-ai/openclacky, covering smart commit skill, critical requirement: single-line commits only, core philosophy, usage and process steps.