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 git-clean-commit-guardgit 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/git-clean-commit-guard)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/git-clean-commit-guard"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/git-clean-commit-guard/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/git-clean-commit-guard"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/git-clean-commit-guard.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 | $0.00043 | $0.00504 |
| Opus 5.5 | $0.00017 | $0.00202 |
| Sonnet 5.5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
git-clean-commit-guard 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
Git clean commit guard
A good commit starts before the message. This skill is the pre-commit hygiene pass: reduce staging noise, isolate one logical change, and catch the files that should never ride along.
What this skill does
It does not write the final commit message. It prepares the diff so a later commit or review step can succeed.
Guard workflow
- Inspect the repo state
git statusgit diffgit diff --staged
- Split logical changes
- If the diff mixes unrelated work, stop and split it before committing
- Remove accidental files
- local config
- generated artifacts
- debug output
- unrelated lockfile churn
- credentials / secrets
- Check commit scope integrity
- Bug fix + test together is fine
- Feature + refactor + docs usually needs separation
- Propose explicit staging
- Prefer file-by-file
git add <path> - Avoid blanket staging commands
- Prefer file-by-file
Things that should trigger a block
.env, credentials, tokens, keys, passwords- build output or generated snapshots with no clear reason
- staged files unrelated to the stated task
- opportunistic refactors bundled into a fix commit
- a lockfile change without a matching dependency reason
Preferred output
Commit hygiene result: Pass | Pass with nits | Block
Keep staged:
- <paths>
Unstage / remove:
- <paths>
Reason:
- <scope contamination or safety risk>
Suggested next command set:
- git restore --staged ...
- git add ...
Anti-patterns
- Starting with the commit message — first clean the diff, then name it.
- Using
git add .out of laziness — that is how local junk enters history. - Treating "mostly related" as good enough — future bisect and review quality collapse fast.
- Letting secrets rely on luck — always perform an intentional safety scan.
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 · 72 lines · 43 tokens per session scan A 469e056416f7
git-clean-commit-guard is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 504 once invoked, about $0.0002 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
aif-git
Run Git staging, commits, pushes and merges with conventional commits, auto-split by type/scope, and secret scanning.
git-workflow-management
Git workflow automation skill for commit message generation, branch management, pre-commit checks, and change history analysis.
re0-git
Rewrite a finished commit's message into a clean, handoff-ready form in your own log style, so git log alone tells the story. User-invoked: run it after a commit.
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.
git-workflow
Git operations: commits, branches, PRs, and conflict resolution.
stepwise-task-execution
Master workflow for an implementation task. Use when you pick up any task or bug that changes product code, including a needrevision bounce.