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 emiliosheinz/agent-skills --skill commit-message-generatorgit clone --depth 1 https://github.com/emiliosheinz/agent-skillsWrote 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/emiliosheinz/agent-skills/commit-message-generator)<a href="https://agentmods.dev/skills/emiliosheinz/agent-skills/commit-message-generator"><img src="https://agentmods.dev/badge/skills/emiliosheinz/agent-skills/commit-message-generator.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 5.1 | $0.00081 | $0.02024 |
| Opus 5 | $0.00041 | $0.01012 |
| Sonnet 5 | $0.00016 | $0.00405 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
commit-message-generator 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 6d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message Generator
Turn the current git state into one or more well-formed Conventional Commit
messages, each confirmed by the user before the commit lands. Never guess
what changed — scripts/analyze-diff.py is the single source of truth.
Hard rules
- Always run
scripts/analyze-diff.pyfirst. Never read the diff manually, never callgit diff/git status/git ls-filesyourself. The script's output is the only input you use to plan groups and write messages. - Staged wins. If the script reports
State: staged, work with the staged files only. Ignore unstaged / untracked files — the user staged what they meant to stage. - If the script exits non-zero (nothing to commit), stop and tell the user.
- Never commit without explicit user confirmation. Print the message,
wait for a yes/edit/no response, then act. Never pass
--no-verify, never amend, nevergit push. - Never add co-author trailers unless the user explicitly asks.
- Never
git add -A/git add .. Stage exactly the paths for the current group and nothing else.
Process
Step 1 — Inspect state
Run the analyzer:
python3 <skill-dir>/scripts/analyze-diff.py
Two possible states:
State: staged→ skip to Step 3 (message generation for the staged diff).State: unstaged→ continue with Step 2 (propose groups).
Step 2 — Propose commit groups (unstaged state only)
Read Files and propose 1–4 logical commit groups. Apply the heuristics
below. Then:
-
1 group → stage all files with
git add -- <paths>and go to Step 3. Show the user the single-group plan first only if there is visible ambiguity; otherwise stage silently and move on. -
2+ groups → print a numbered proposal like:
Proposed 2 commits: [1] feat(api): <files...> [2] docs: README.md, CHANGELOG.md Confirm? (yes / edit / merge / cancel)Responses:
yes/lgtm→ iterate groups in order (see Sequential loop).edit(or free-form feedback like "move X to group 2", "split group 1") → revise the proposal, re-print, re-prompt.merge→ treat everything as one group; stage all, go to Step 3.cancel/no→ stop. Do not stage anything.
What ships with it
3 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.
- 6d ago First seen · 201 lines · 81 tokens per session scan A e315be3c982d
commit-message-generator is a skill published in the GitHub repository emiliosheinz/agent-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,024 once invoked, about $0.0004 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 skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…