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 orlando-japan/claude-code-setting --skill commit-smartgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/commit-smart)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/commit-smart"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/commit-smart/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/orlando-japan/claude-code-setting/commit-smart"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/commit-smart.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 | $0.00031 | $0.00672 |
| Opus 5.5 | $0.00012 | $0.00269 |
| Sonnet 5.5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
commit-smart 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit smart
The commit message is the one artifact a future bisector will read. Make it earn its keep.
Format
Conventional Commits, lightweight:
<type>(<scope>): <imperative subject>
<body: why, not what>
<footer: refs, breaking notes>
Types: feat, fix, refactor, test, docs, chore, perf, build, ci.
Subject rules: imperative mood, lowercase, no trailing period, ≤72 chars.
The subject
- Good:
fix(auth): redirect logged-out users with return_to - Good:
refactor(db): extract connection pooling into pool.ts - Bad:
Fixed a bug(vague, past tense) - Bad:
Update auth.ts(what file, not what change) - Bad:
Fix: fix the fix for the auth issue(noise)
The body — why, not what
The diff shows what changed. The body answers:
- What was the problem this solves?
- What constraint forced this particular solution?
- What alternative did you consider and reject, and why?
Skip the body for obvious changes: typo, dep bump, version tag.
Example:
fix(auth): redirect logged-out users with return_to
Users who bookmarked /settings and were logged out were landing
on /login with no path back. They had to navigate manually after
logging in, and ~15% bounced.
Alternative considered: store return_to in a cookie on the 401.
Rejected because cookies persist across sessions and can leak
stale redirects.
One logical change per commit
- Bug fix + its test: one commit (they prove each other).
- Feature + unrelated refactor: two commits.
- Rename + functional change: two commits (the rename comes first, makes the second reviewable).
If git diff --staged shows changes that don't belong together, unstage and split.
What never goes in a commit
- Secrets. Check
git diff --staged | grep -iE '(token|secret|key|password)'before every commit. - Large binaries. Use LFS or a bucket.
- Generated files your build produces.
console.log,print(),binding.pryleft over from debugging.- Commented-out code.
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 · 87 lines · 31 tokens per session scan A c07d1ded8fb0
commit-smart is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 672 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
conventional-commit-message
Generate high-quality Conventional Commit messages for repositories using conventional-changelog-conventionalcommits.
git-workflow
Use when naming or scoping a branch, writing or fixing a commit message, picking the gitmoji for a commit, untangling history (rebase versus merge versus squash), or cutting a versioned release — the portable git-convention layer for any repo. Covers gitmoji + Conventional Commits, SemVer tags, branch hygiene…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
git-commit
Safely orchestrate Conventional Commits for staged Git changes, or all working-tree changes when the user explicitly asks to include everything. Use when asked to write a commit message, split staged or working-tree changes, organize a messy index, or draft commit text without pushing. Auto-detects commit language…
git-authoring
Authors and executes git work end to end — Conventional Commits messages, pull-request content, release notes, and pull-request review, plus the repository operations an engineer runs daily: branching, rebasing, squashing, cherry-picking, reverting, merge-conflict resolution, stashes, tags, remotes, and recovery…
stage
Use when committing work from the current session to stage ONLY hunks the session touched, not the entire file. Prevents accidentally staging unrelated uncommitted changes from other work.