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/alirezarezvani/claude-code-tresor/git-commit-helpernpx skills add alirezarezvani/claude-code-tresor --skill git-commit-helpergit clone --depth 1 https://github.com/alirezarezvani/claude-code-tresorWhat 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 | $0.00055 | $0.01858 |
| Opus 5 | $0.00028 | $0.00929 |
| Sonnet 5 | $0.00011 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
git-commit-helper 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Helper Skill
Generate conventional commit messages from your git diff.
When I Activate
- ✅
git commitwithout message - ✅ User asks "what should my commit message be?"
- ✅ Staged changes exist
- ✅ User mentions commit or conventional commits
- ✅ Before creating commits
What I Generate
Conventional Commit Format
<type>(<scope>): <subject>
<body>
<footer>
Types:
feat: New featurefix: Bug fixdocs: Documentation changesstyle: Code style (formatting, no logic change)refactor: Code refactoringperf: Performance improvementstest: Test additions or fixesbuild: Build system changesci: CI/CD changeschore: Maintenance tasks
Examples
Feature Addition
# You staged:
git add auth.service.ts login.component.tsx
# I analyze diff and suggest:
feat(auth): add JWT-based user authentication
- Implement login/logout functionality
- Add token management service
- Include auth guards for protected routes
- Add unit tests for auth service
Closes #42
Bug Fix
# You staged:
git add UserList.tsx
# I suggest:
fix(components): resolve memory leak in UserList
Fixed subscription not being cleaned up in useEffect,
causing memory leak when component unmounts.
Closes #156
Breaking Change
# You staged:
git add api/users.ts
# I suggest:
feat(api): update user API response format
Changed response structure to include metadata
for better pagination and filtering support.
BREAKING CHANGE: User API now returns { data, metadata }
instead of direct array. Update client code accordingly.
Documentation Update
# You staged:
git add README.md docs/api.md
# I suggest:
docs: update API documentation with authentication examples
- Add authentication flow diagrams
- Include cURL examples for protected endpoints
- Document error responses
Analysis Process
Step 1: Check Staged Changes
git diff --staged --name-only
git diff --staged
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 383 lines · 55 tokens per session scan A ce957544367f
git-commit-helper is a skill published in the GitHub repository alirezarezvani/claude-code-tresor (768 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,858 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
debug-loop
Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or emitting wrong tool calls.
release-check
Pre-release checklist for Forge — verify, version bump, changelog, docs, docker build, smoke test. Run before tagging v.
verify
Run Forge's canonical verification chain (format:check + lint + typecheck + build + test). Use before claiming any task complete or opening a PR.
add-provider
Scaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked transport.
add-tool
Scaffold a new Forge tool end-to-end — implementation, registration, permission/risk metadata, sandbox routing, and a unit test.
flywheel
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.