Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/commands/georgekhananaev/claude-skills-vault/git-commit)<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/git-commit"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/git-commit.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 | $0.00000 | $0.01018 |
| Opus 5 | $0.00000 | $0.00509 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
git-commit 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Command
IMPORTANT: This command ONLY runs when explicitly invoked via /git-commit. Do NOT auto-commit after code modifications. Wait for user to explicitly run /git-commit.
Goal: Safe, attributed git commit for the configured git user.
1. Identity & Attribution
- Author: Use
git config user.name&git config user.email(linked GitHub account) - Credit: No co-authors/AI attribution unless requested
2. Safety Protocols
Forbidden Files:
- Secrets:
.env,.env.*,*.pem,*.key,id_rsa,secrets.*,credentials.* - Logs:
*.log,npm-debug.log,yarn-error.log - System:
.DS_Store,node_modules/,dist/,build/,__pycache__/,.venv/
Critical Flags:
- No
--no-verify(hooks must pass) - No
--no-gpg-sign(sign if GPG configured) - No
--amend(unless fixing immediate prev commit)
3. Auto-Regenerate Docs (if needed)
Before staging, check if any skills, commands, or scripts changed:
git diff --name-only HEAD ; git ls-files --others --exclude-standard
If changes touch .claude/skills/, .claude/commands/, or scripts/:
node scripts/generate-manifest.js # manifest.json + cli/manifest.json
node scripts/generate-docs.js # SKILLS.md, COMMANDS.md, cli/README.md
node scripts/generate-notice.js # NOTICE
Then include the regenerated files in the commit.
If no skill/command/script changes: skip regeneration.
4. Execution Flow
git status- check stategit diff- review (stop if secrets/debug found)- Check if
.claude/skills/,.claude/commands/, orscripts/changed → regenerate docs if so - Stage:
git add <file>(use-pfor mixed changes, avoidgit add .w/ junk) - Construct message (Conventional Commits)
git commit -m "..."git status- verify
5. Commit Message Standard
Format: <type>(<scope>): <description>
| Type | Desc |
|---|---|
| feat | new feature |
| fix | bug fix |
| docs | docs only |
| style | formatting |
| refactor | no fix/feat |
| perf | performance |
| test | tests |
| build | build/deps |
| ci | CI config |
| chore | other |
| revert | revert commit |
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 · 141 lines · 0 tokens per session scan A 19d6189f5e49
git-commit is a command published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,018 tokens. 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 commands, from other repositories
quick-commit
Quick commit with automatic formatting, linting, and conventional commit message.
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).
commit
Analyze Git changes and generate a conventional commit message following the Commitizen format.
commit
Generate a concise commit message for staged changes and commit.
fixup
Apply staged changes to a selected commit in history (rewrites history).
commit-push-pr
建立一個 Git 提交、推送到遠端，並開啟一個 Pull Request.