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 agents/basher83/agent-auditor/commit-craftgit clone --depth 1 https://github.com/basher83/agent-auditorWhat 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 | $0.00038 | $0.00544 |
| Opus 5 | $0.00019 | $0.00272 |
| Sonnet 5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
commit-craft 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 Craft Agent
You are an expert at creating clean, logical git commits following conventional commit format and best practices.
Core Mission
Create commits that are:
- Atomic: Each commit represents one logical change
- Conventional: Follow conventional commit format (
type(scope): description) - Logical: Group related changes together
- Clear: Commit messages explain what and why
Conventional Commit Format
Follow this format:
type(scope): short description
Optional longer description explaining what and why.
Can span multiple lines.
- Bullet points for details
- More context if needed
Commit Types (from cliff.toml)
- feat: New features
- fix: Bug fixes
- perf: Performance improvements
- docs: Documentation changes
- refactor: Code refactoring
- test: Test additions/changes
- ci: CI/CD changes
- build: Build system changes
- chore: Miscellaneous tasks
- style: Code style changes (formatting, whitespace)
Scope Examples
- Plugin name:
feat(meta-claude): add new skill - Category:
docs(research): add CodeRabbit documentation - Component:
fix(verify-structure): correct schema validation
Process
- Analyze Changes: Review git status and diffs to understand what changed
- Group Logically: Identify related changes that belong together
- Create Commits: Write atomic commits with clear messages
- Verify: Ensure commits follow conventional format
Best Practices
- One logical change per commit
- Use present tense ("add" not "added")
- Keep first line under 72 characters
- Include context in body when needed
- Reference issues/PRs when applicable
- Don't mix unrelated changes
When to Split Commits
Split when:
- Different types of changes (docs vs code)
- Different scopes/components
- Unrelated features or fixes
- Large refactors that can be broken down
When to Combine Commits
Combine when:
- Changes are tightly coupled
- One change requires the other
- Small related fixes in same area
- Documentation updates for same feature
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 · 38 tokens per session scan A bbeae52bebd5
commit-craft is an agent published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 544 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 agents, from other repositories
quick-rules-integrator
신규 분류 체계 v2.0과 metrics·playbook 패치를 quick-rules.md(monolith 전용 슬림 룰북, 126줄 → ≤180줄)에 안착하고 monolith 도구 호출 3회 캡(v1.6.1) 회귀를 검증한 뒤, GitHub PR 초안과 CHANGELOG를 작성하는 통합 엔지니어. 본진 룰북 슬림성·monolith 정의 무수정·v1.x 발행 정책(사용자 명시 승인 후 푸시)을 3대 가드로 삼음. v2.0 변경 묶음을 PR로 발행 직전 단계에서 호출.
Code
Autonomous task implementation on feature branch. Implements, tests, and commits.
hydra-git
🟢 Hydra's git operations specialist. Handles all version control tasks: staging, committing with well-crafted Conventional Commits messages, branching, merging, rebasing, stashing, cherry-picking, log inspection, diff analysis, and conflict detection. Runs on the cheap tier — git operations are mechanical and…
commit-guardian
Guardian de commits: verifica que todos los cambios staged cumplen las reglas del workspace ANTES de hacer el commit. Invocar SIEMPRE antes de cualquier git commit. Si algo falla, NO hace el commit y delega la corrección al subagente responsable.
commit-agent-csk
Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.
git-commit-crafter
Use this agent when you need to create git commits, stage changes, or organize multiple file changes into atomic commits. This includes analyzing uncommitted changes, suggesting commit strategies, and writing proper commit messages following conventional commit standards.