committing

committing is a skill for Claude Code, Codex from notorious-ai/claude-plugins. It costs 40 tokens per session (2,052 once invoked), scanned A, original, MIT.

A guide for writing commit messages in Go-focused code repositories. It covers commits for Go code as well as related documentation, configuration, automation, and scripts.

In plain words
What is it for?
Use it when preparing commits in a repository with Go code, typically one containing a go.mod file. It helps inspect existing history and match the project’s local wording conventions.
Why use it?
It removes uncertainty about how to describe changes consistently. It also encourages commit messages that explain the change and its broader reason clearly.

Skill for Claude CodeCodex

Part of the golang-dev plugin — 3 skills shipped together

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.

agentmods
npx agentmods add skills/notorious-ai/claude-plugins/committing
Any agent
npx skills add notorious-ai/claude-plugins --skill committing
Clone the repo
git clone --depth 1 https://github.com/notorious-ai/claude-plugins

Made for: Claude Code, Codex.

Or install golang-dev, the plugin that ships this one along with the rest of its 3 skills.

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 committing

README.md
[![agentmods](https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/committing.svg)](https://agentmods.dev/skills/notorious-ai/claude-plugins/committing)
Your own site
<a href="https://agentmods.dev/skills/notorious-ai/claude-plugins/committing"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/committing.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.02052
Opus 5 $0.00020 $0.01026
Sonnet 5 $0.00008 $0.00410
Haiku 4.5 $0.00004 $0.00205

Measured 5d ago against content hash b7abed0e381c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

committing 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 5d 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.

golang-dev/skills/committing/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Committing in Go Projects

Write commit messages that match Go project conventions - for Go packages and all supporting files (docs, configs, CI, scripts) in Go-centric codebases.

Core Principles

Commits tell the story of a codebase. Follow these rules for every commit:

  1. Describe HOW the target changes, not WHAT you did as a developer
  2. Think: "This change modifies TARGET to _____"
  3. Use plaintext only - no Markdown formatting in commit messages
  4. Respect local repository conventions while maintaining Go team style
  5. Keep the body in its lane: the diff is the WHAT, file comments are the WHY-INTRINSIC, the commit body is the WHY-EXTRINSIC
  6. Write as the human engineer making the change, not as the agent executing a task - never echo prompts or instructions

Workflow

When generating a commit message:

1. Inspect Changes

git diff --cached    # staged changes
git diff             # if nothing staged

2. Check Local Conventions

Before deciding on target format, check how similar files were committed:

git log --oneline -10 -- <changed-file>
git log --oneline -20

Look for patterns:

  • Does this repo use ci: or github: for workflow files?
  • What package path depth is used for Go code?
  • Are there domain-specific prefixes?

Respect local conventions when they exist and are consistent.

3. Determine Content Type

Classify the changes to load appropriate guidance:

Content Type Files Load Reference
Go packages *.go files in module paths references/go-package-commits.md
Non-Go content docs, configs, CI, scripts references/non-go-commits.md
Mixed changes Both types Consider splitting into separate commits

4. Identify Target

Apply the decision algorithm from the appropriate reference file.

Quick reference for targets:

Category Target Format Example
Go package pkg or pkg/sub net/http:, context:
Documentation docs: All .md files, docs/
GitHub github: .github/ directory
Claude Code claude: CLAUDE.md, .claude/, plugin.json
Agents agents: agents/ directory
Git config git: .gitignore, .gitattributes
Dependencies go.mod: Module changes
Build build: Makefile, build scripts
CI (non-GitHub) ci: CI configuration
Tool config Tool name golangci:, docker:

Read the full file on GitHub · 240 lines

Files

What ships with it

5 files 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. 5d ago First seen · 240 lines · 0 tokens per session scan A b7abed0e381c

Subscribe to this mod's changes

committing is a skill published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 2,052 once invoked, about $0.0002 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.