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/orlando-japan/claude-code-setting/commit-smartnpx skills add orlando-japan/claude-code-setting --skill commit-smartgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWhat 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 | $0.00031 | $0.00672 |
| Opus 5 | $0.00015 | $0.00336 |
| Sonnet 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 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 — 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.
- 2d 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 3mo ago), licensed MIT. It adds 31 tokens to every session and 672 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
conventional-commit-message
Generate high-quality Conventional Commit messages for repositories using conventional-changelog-conventionalcommits.
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…
Git Commit Writer
Generates conventional commit messages from staged changes or a diff.
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.