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/bkircher/skills/git-commit-messagenpx skills add bkircher/skills --skill git-commit-messagegit clone --depth 1 https://github.com/bkircher/skillsWhat 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 | $0.00015 | $0.00681 |
| Opus 5 | $0.00008 | $0.00341 |
| Sonnet 5 | $0.00003 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
git-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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a commit message for the staged changes. If changes are staged, return only the commit message, with no code fence or commentary. Otherwise, report that nothing is staged.
Inspect the staged changes
List the staged files:
If this produces no output, report that nothing is staged and do not invent a message. Otherwise, read the complete staged diff:
Use the conversation context to understand the rationale, but describe only the staged diff. Ignore unstaged and untracked changes.
Inspect the repository style
Read recent non-merge commit subjects before drafting the message:
Match the established style. Use Conventional Commit syntax such as
feat(scope): ... or fix(scope): ... only when it clearly dominates recent
history. Isolated examples and component prefixes such as subdir: ... do not
establish that convention.
Use concise, natural language
- Prefer plain, slightly informal engineering language over formal wording.
- When unambiguous, prefer
infra,config,prod, anddevoverinfrastructure,configuration,production, anddevelopment. - Preserve exact names from the staged diff and follow established repository terminology when it differs.
Write the subject
- Limit the subject to 50 characters.
- Use the imperative mood:
fix, notfixedorfixes. - Do not end the subject with a period.
- When changes affect one clear component and history uses component prefixes,
use
<component>: <imperative summary>and match the casing used in recent history. Otherwise, capitalize the first word of an unprefixed subject.
Write the body
Use this format unless the subject fully describes one small, self-explanatory change:
<subject>
Changes:
- <change or rationale>
- <change or rationale>
- Separate the body from the subject with a blank line.
- Keep every body line within 72 characters, including indentation.
- Explain what changed and why without repeating the subject or including unnecessary implementation details.
- Use only as many bullets as needed; do not invent items to reach a fixed count.
- Do not end a one-line bullet with a period.
- Wrap bullets at word boundaries and indent continuation lines by two spaces.
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.
- 2d ago First seen · 104 lines · 15 tokens per session scan A 29df2af934f6
git-commit-message is a skill published in the GitHub repository bkircher/skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 681 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…