commit-code

commit-code is a skill for Claude Code, Codex from marmot-protocol/agent-config. It costs 27 tokens per session (911 once invoked), scanned A, original, MIT.

A workflow for creating Git commits with commit-message analysis and safety checks. Git is a system for recording changes to code over time.

In plain words
What is it for?
Use it when you need to commit staged changes, including reviewing the proposed message and creating the final commit.
Why use it?
It provides a repeatable process for checking staged files, choosing a suitable commit type and message, and verifying the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when you need to commit staged changes, including reviewing the proposed message and creating the final commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marmot-protocol/agent-config/commit-code
Install

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.

Any agent
npx skills add marmot-protocol/agent-config --skill commit-code
Clone the repo
git clone --depth 1 https://github.com/marmot-protocol/agent-config

Made for: Claude Code, Codex.

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-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/marmot-protocol/agent-config/commit-code/github.svg)](https://agentmods.dev/skills/marmot-protocol/agent-config/commit-code)
Your own site
<a href="https://agentmods.dev/skills/marmot-protocol/agent-config/commit-code"><img src="https://agentmods.dev/badge/skills/marmot-protocol/agent-config/commit-code/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-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/marmot-protocol/agent-config/commit-code"><img src="https://agentmods.dev/badge/skills/marmot-protocol/agent-config/commit-code.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 911 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 $0.00911
Opus 5.5 $0.00011 $0.00364
Sonnet 5.5 $0.00005 $0.00182
Haiku 4.5 $0.00003 $0.00091

Measured 1mo ago against content hash 9331a31904ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-code 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.

opencode/skills/commit-code/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Code Skill

You are creating git commits using Ren's commit tools. This skill covers the full workflow from staged changes to verified commit.

Activation

This skill activates when:

  • User asks to commit changes
  • User says "commit this" or "create a commit"
  • Context involves staged git changes ready to commit
  • User wants to finalize their work with a commit

Tools

Tool Purpose
commit_message Analyze staged changes, suggest type/scope/subject
commit Create the actual git commit with safety checks
diff-analyze Get detailed breakdown of changes (optional)

Workflow

Step 1: Check Staged Changes

Before anything else, verify there are staged changes:

git diff --cached --stat

If nothing is staged:

  • Inform the user
  • Suggest files they might want to stage
  • Stop the workflow

Step 2: Analyze Changes

Use the commit_message tool to analyze staged changes:

commit_message({ includeBody: true })

This returns:

  • type - Inferred commit type (feat, fix, docs, etc.)
  • scope - Common directory scope (or null)
  • subject - Suggested subject line
  • body - Change statistics
  • files - List of staged files
  • breaking - Whether breaking changes detected

Step 3: Draft Commit Message

Based on the analysis, draft a conventional commit message:

<type>(<scope>): <subject>

<body explaining what and why>

<footer with issue references>

Always present the message to the user before committing.

Step 4: Create the Commit

Use the commit tool with the full message:

commit({ message: "feat(auth): add password reset\n\nImplement reset flow with email verification.\n\nCloses #42" })

The tool returns:

  • success - Whether commit was created
  • hash - Short commit hash (on success)
  • summary - Commit summary line (on success)
  • error - Error message (on failure)
  • hint - Suggestion for fixing the error

Step 5: Report Result

On success:

✓ Commit created: a1b2c3d feat(auth): add password reset

Read the full file on GitHub · 147 lines

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. 1mo ago First seen · 147 lines · 27 tokens per session scan A 9331a31904ff

Subscribe to this mod's changes

commit-code is a skill published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 8mo ago), licensed MIT. It adds 27 tokens to every session and 911 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.