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 Jewgah/claude-code-skills --skill commitgit clone --depth 1 https://github.com/Jewgah/claude-code-skillsWrote 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/jewgah/claude-code-skills/commit)<a href="https://agentmods.dev/skills/jewgah/claude-code-skills/commit"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/commit/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/jewgah/claude-code-skills/commit"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/commit.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 | $0.00015 | $0.01084 |
| Opus 5.5 | $0.00006 | $0.00434 |
| Sonnet 5.5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit & Self-Maintain CLAUDE.md + Memory
Step 1: Commit
- Run
git status(never use-uall),git diff --cached, andgit log --oneline -5in parallel. - Analyze all staged changes. Draft a concise commit message:
- Use conventional commits:
feat:,fix:,refactor:,docs:,chore:, etc. - Focus on why, not what.
- NEVER include
Co-Authored-Bylines or mention Claude.
- Use conventional commits:
- Stage relevant untracked files if needed (prefer specific files over
git add .). - Commit using a HEREDOC for the message. Do NOT use
--no-verify. - Run
git statusto confirm success.
Step 2: Update ROADMAP.md
After committing, update ROADMAP.md at the project root.
- Gitignore rule:
ROADMAP.mdshould normally be tracked by git and committed alongside the changes it describes. Only leave it gitignored if that specific repo already does so. - Read the current
ROADMAP.md(create it if it doesn't exist). - Prepend a new entry at the top (most recent first) with this format:
## [commit hash short] - [commit message] ([date YYYY-MM-DD])
**Problem:** [What was wrong or missing - 1-2 sentences]
**Solution:** [What was done to fix/implement it - 1-2 sentences]
**Files changed:** [list of key files touched, not exhaustive]
---
- Keep entries concise and useful. Focus on the why and the how, not line-by-line diffs.
- If the commit is trivial (typo fix, formatting), still add an entry but keep it minimal.
Step 3: Evaluate CLAUDE.md Relevance
After committing, read the project's CLAUDE.md (if one exists) and review the committed diff against it.
Update CLAUDE.md ONLY if the commit changed something the file already documents or should document:
- A new backend function/endpoint/service → add to whatever list tracks those
- A new data model/entity/schema → add to whatever list tracks those
- A changed core flow (auth, payments, data pipeline, etc.) → update the relevant section
- A new critical constraint or gotcha discovered → add to constraints/warnings section
- An architecture shift (new library, new pattern, new convention) → update architecture docs
- A removed or renamed component that CLAUDE.md references → fix the stale reference
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 · 93 lines · 15 tokens per session scan A b4b93a107cf2
commit is a skill published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,084 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 2026-09-14.
Other skills, from other repositories
antfu-create-pr
Create a reviewable GitHub pull request from the current branch with a Conventional Commits title, a concise evidence-based body, and before/after screenshots for UI changes. Use when asked to open, create, publish, or prepare a PR.
git-workflow
Git best practices, branching strategies, commit conventions, and code review patterns.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
implement-suggestion
Implements review-comment suggestions across one or more PRs. Multi-PR mode (default when $ARGUMENTS holds PR URLs; empty $ARGUMENTS auto-detects the active PR) resolves a worktree per PR, fetches every actionable comment from human teammates AND AI review bots (claude[bot], coderabbitai[bot], …), validates each…
pr-review
One-shot read-only review of a GitHub PR — dispatches the pr-reviewer agent and reports its verdict and findings without touching your code. The short entry point for "review this PR" when you do not want an apply-and-converge loop. Also writes maintainer relevance rules via /pr-review remember . Invoke with…