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/noahlz/claude-plugins/commit-onlynpx skills add noahlz/claude-plugins --skill commit-onlygit clone --depth 1 https://github.com/noahlz/claude-pluginsWhat 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 | $0.00027 | $0.00715 |
| Opus 5 | $0.00014 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
commit-only 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a git commit with Claude attribution.
Activate only when user invokes /commit-only or asks to commit (e.g. "commit", "commit my changes", "just commit", "commit without costs").
SKILL_BASE_DIR: ${CLAUDE_SKILL_DIR}
If the above shows literal ${CLAUDE_SKILL_DIR}, halt: "Requires Claude Code 2.1.69+."
Rules
- DELEGATE_TO: Read the referenced file with the Read tool, then execute its instructions exactly. Never improvise or guess commands.
- Narration: Only narrate steps marked STEP_DESCRIPTION. Execute all others silently — do NOT output or summarize intermediate values.
Checklist
- [ ] 0. Pre-flight check
- [ ] 1. Detect or generate commit message
- [ ] 2. Get user approval
- [ ] 3. Create commit
- [ ] 4. Display summary
0. Pre-flight check
Halt if git commands already ran in this turn.
1. Detect or Generate Commit Message
Check conversation for an existing Proposed commit message: block (e.g. from /preview-commit-message).
If found: Extract COMMIT_SUBJECT and COMMIT_BODY from the ━━━-delimited block. Skip to Step 2.
If not found:
DELEGATE_TO: ../../references/stage_and_analyze.md
DELEGATE_TO: ../../references/message_guidelines.md
Store COMMIT_SUBJECT and COMMIT_BODY. Produce no output yet — the message is displayed in Step 2 via the AskUserQuestion question field.
2. Get User Approval
Obtain user approval via AskUserQuestion before proceeding. The commit message MUST be embedded in the question field (see reference) — this overrides the Narration silent rule.
DELEGATE_TO: ../../references/message_approval.md
- "use_full" or "use_subject_only" → Step 3
- "request_revisions" → return to Step 1
3. Create Commit
STEP_DESCRIPTION: "Creating git commit"
Verify APPROVAL_STATUS is "use_full" or "use_subject_only". If not, exit.
The final -m adds the Claude attribution trailer as its own paragraph so git parses it as a trailer.
If COMMIT_BODY is non-empty:
git commit -m "{{COMMIT_SUBJECT}}" -m "{{COMMIT_BODY}}" -m "Co-Authored-By: Claude Code <[email protected]>"
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 · 95 lines · 27 tokens per session scan A 4191bcda6d48
commit-only is a skill published in the GitHub repository noahlz/claude-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 715 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…