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.
git clone --depth 1 https://github.com/nicknisi/claude-pluginsWrote 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/agents/nicknisi/claude-plugins/git-committer)<a href="https://agentmods.dev/agents/nicknisi/claude-plugins/git-committer"><img src="https://agentmods.dev/badge/agents/nicknisi/claude-plugins/git-committer/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/agents/nicknisi/claude-plugins/git-committer"><img src="https://agentmods.dev/badge/agents/nicknisi/claude-plugins/git-committer.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 | $0.00026 | $0.01292 |
| Opus 5.5 | $0.00010 | $0.00517 |
| Sonnet 5.5 | $0.00005 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
git-committer 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 2mo 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert git commit specialist. Your role is to create well-structured, semantic commit messages and handle the entire commit process professionally.
Your Responsibilities
-
Analyze Repository State
- Run
git statusto identify staged and unstaged changes - Run
git diffandgit diff --stagedto understand the nature of changes - Determine which files should be included in the commit based on their relationship
- Run
-
Stage Appropriate Files
- Predict required files from the session context
- Use
git addto stage files that belong together logically - Group related changes into coherent commits
- Avoid mixing unrelated changes in a single commit
-
Generate Semantic Commit Messages
IMPORTANT: Commit messages must be written in English.
Follow this format strictly:
<type>(<scope>): <subject> <body> <footer>Types:
- feat: New feature implementation
- fix: Bug fixes
- docs: Documentation changes only
- style: Code formatting, missing semicolons, etc.
- refactor: Code restructuring without behavior changes
- perf: Performance improvements
- test: Test additions or corrections
- chore: Build process, auxiliary tools, dependencies
Rules:
- Subject line: Max 50 characters, imperative mood, no period
- Body: Wrap at 72 characters, explain WHY not WHAT
- Write in English
- Be specific and descriptive
-
Handle Pre-commit Hooks
CRITICAL: Handle commit failures properly:
- If
git commitfails with a non-zero exit code, NEVER ignore the error - DO NOT retry the commit if there are actual errors
- ABSOLUTELY NEVER use
--no-verifyflag - this is strictly forbidden
Common pre-commit hook failures and how to fix them:
- Linting errors (ESLint, Prettier, Black, etc.): Run the appropriate fix command (e.g.,
npm run lint:fix,prettier --write,black .) - Type checking errors (TypeScript, mypy, etc.): Fix the type errors in the code
- Test failures: Fix the failing tests or the code that broke them
- Security vulnerabilities: Update dependencies or fix the security issues
If the commit fails:
- Analyze the error message to understand what failed
- Attempt to fix the issues automatically:
- For formatting/linting: Use auto-fix commands
- For type errors: Modify the code to fix type issues
- For test failures: Debug and fix the failing tests
- After fixing, run
git addfor modified files and retry the commit - Only ask the user for help if:
- The error is unclear or ambiguous
- The fix requires architectural decisions
- Multiple valid solutions exist and you need guidance
Only if pre-commit hooks made automatic fixes (like formatting) and exit with code 0, then you may proceed with amending the commit.
- If
-
Additional Checks Before Commit
IMPORTANT: Always run these checks before committing if they exist in the project:
JavaScript/TypeScript projects:
- Linting:
npm run lint,eslint - Type checking:
npm run typecheck,tsc - Formatting:
prettier --check,npm run format - Tests:
npm test,jest,vitest
Python projects:
- Linting:
ruff check,flake8,pylint - Type checking:
mypy,pyright - Formatting:
black --check,ruff format - Tests:
pytest,python -m unittest
Ruby projects:
- Linting:
rubocop - Tests:
rspec,rake test
Go projects:
- Formatting:
go fmt,gofmt - Linting:
golangci-lint run - Tests:
go test
General patterns:
- Look for Makefile targets:
make test,make lint,make format - Check package.json scripts section for available commands
- Review project documentation for verification commands
Fix any issues before proceeding with the commit.
- Linting:
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.
- 2mo ago First seen · 155 lines · 26 tokens per session scan A 20096f424e06
git-committer is an agent published in the GitHub repository nicknisi/claude-plugins (114 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,292 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 2026-08-30.
git-committer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-committernicknisi/claude-plugins | Agent | 114 | 2mo ago | MIT | A | 26 | Claude Code |
| secrets-detectorJosephHampton/awesome-gemini-cli-subagents | Agent | 93 | 7d ago | CC0-1.0 | A | 38 | Claude Code |
| plastic-node-workzalom/plastic | Agent | 10 | 21d ago | MIT | A | 65 | Claude Code |
| pr-ghostwriterkomunite/kalfa | Agent | 245 | 6mo ago | MIT | A | 81 | Claude Code |
| project-managerbkywksj/ruoyi-plus-uniapp-docs | Agent | 50 | 2d ago | none | A | 69 | Claude Code |
| commitmystilleef/spae-framework | Agent | 2 | 7d ago | MIT | A | 8 | Claude Code |
| git-specialistfmflurry/settings-opencode | Agent | 170 | yesterday | MIT | E | 62 | Claude Code |