commit-only

commit-only is a skill for Claude Code from noahlz/claude-plugins. It costs 27 tokens per session (688 once invoked), scanned A, original, MIT.

A skill for committing already-staged Git changes with an AI-generated commit message and Claude attribution, without recording cost metrics.

In plain words
What is it for?
Use it after changes are staged when the user asks to commit them without costs. Git is the version-control system used to record project changes.
Why use it?
It provides a defined commit workflow when the user wants a regular commit and does not want cost tracking.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev-workflow plugin — 10 skills, 4 agents shipped together

Good fit Use it after changes are staged when the user asks to commit them without costs. Git is the version-control system used to record project changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add noahlz/claude-plugins
Claude Code
/plugin install dev-workflow

Made for: Claude Code.

Or install dev-workflow, the plugin that ships this one along with the rest of its 10 skills, 4 agents.

Wrote 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.

agentmods badge for commit-only

README.md
[![agentmods](https://agentmods.dev/badge/skills/noahlz/claude-plugins/commit-only/github.svg)](https://agentmods.dev/skills/noahlz/claude-plugins/commit-only)
Your own site
<a href="https://agentmods.dev/skills/noahlz/claude-plugins/commit-only"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/commit-only/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.

agentmods 80×15 button for commit-only

Your own site · 80×15
<a href="https://agentmods.dev/skills/noahlz/claude-plugins/commit-only"><img src="https://agentmods.dev/badge/skills/noahlz/claude-plugins/commit-only.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 688 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00688
Opus 5.5 $0.00011 $0.00275
Sonnet 5.5 $0.00005 $0.00138
Haiku 4.5 $0.00003 $0.00069

Measured 8d ago against content hash 6a88670b66e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 8d 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.

plugins/dev-workflow/skills/commit-only/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 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").

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: ${CLAUDE_PLUGIN_ROOT}/references/stage_and_analyze.md

DELEGATE_TO: ${CLAUDE_PLUGIN_ROOT}/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: ${CLAUDE_PLUGIN_ROOT}/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]>"

Read the full file on GitHub · 91 lines

Files

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.

Changes

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.

  1. 8d ago Changed · -4 lines 6a88670b66e4
  2. 1mo ago First seen · 95 lines · 27 tokens per session scan A 4191bcda6d48

Subscribe to this mod's changes

commit-only is a skill published in the GitHub repository noahlz/claude-plugins (5 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 688 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 2026-08-31.