git-commit-message

A tool that suggests Git commit messages from staged changes. A commit is a saved set of changes in Git, and Conventional Commits are a standard format for describing what changed.

In plain words
What is it for?
Use it before committing code, from a commit-message hook, or whenever you need a message for added, changed, or deleted files.
Why use it?
It saves time reading a diff and helps keep commit messages consistent and useful to the team.

Skill for Claude CodeCodex

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/artivilla/agents-config/git-commit-message
Any agent
npx skills add artivilla/agents-config --skill git-commit-message
Clone the repo
git clone --depth 1 https://github.com/artivilla/agents-config

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,768 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 $0.00037 $0.03768
Opus 5 $0.00018 $0.01884
Sonnet 5 $0.00007 $0.00754
Haiku 4.5 $0.00004 $0.00377

Measured yesterday against content hash 848ee8294eca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-commit-message 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 yesterday.

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.

skills/git-commit-message/SKILL.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Message Generator

Auto-generates conventional commit messages from git diffs with tiered format enforcement

Purpose

Analyze staged git changes and generate concise, meaningful commit messages following a tiered Conventional Commits specification. This skill examines file modifications, additions, and deletions to infer the type and scope of changes, producing commit messages that match the importance of the change - from detailed documentation for critical features to concise messages for minor updates.

Key Innovation: Three-tier format system that balances thoroughness for critical commits (feat, fix, security) with efficiency for routine changes (docs, chore, style).

When This Skill Activates

  • When /commit-msg command is invoked
  • When invoked from a commit-msg/prepare-commit-msg hook (if installed)
  • When user requests commit message suggestions
  • When analyzing changes before creating a commit

Core Capabilities

1. Diff Analysis

  • Parse git diff --staged output
  • Identify modified, added, and deleted files
  • Analyze code changes (additions, deletions, modifications)
  • Detect patterns across multiple files

2. Change Classification

  • Determine commit type from changes:
    • feat: New features or functionality
    • fix: Bug fixes
    • security: Security fixes or hardening
    • refactor: Code restructuring without behavior change
    • docs: Documentation changes
    • style: Formatting, whitespace, code style
    • test: Adding or modifying tests
    • chore: Build process, dependencies, tooling
    • perf: Performance improvements
    • ci: CI/CD configuration changes
    • build: Build system changes
    • revert: Reverting previous commits

3. Scope Detection

  • Infer scope from file paths and patterns:
    • Directory names (e.g., api, auth, ui)
    • File name patterns (e.g., *.test.jstests)
    • Framework conventions (e.g., components/, services/)

4. Message Generation

  • Format: type(scope): description
  • Enforce tier limits: Tier 1 summary max 50 chars; Tier 2/3 summary max 72 chars (ideal 50)
  • Use imperative mood ("add" not "added")
  • Focus on "what" and "why", not "how"
  • Provide 2-3 alternative suggestions

Read the full file on GitHub · 442 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. yesterday First seen · 442 lines · 37 tokens per session scan A 848ee8294eca

Subscribe to this mod's changes

git-commit-message is a skill published in the GitHub repository artivilla/agents-config (0 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 3,768 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.

Related

Other skills, from other repositories

workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…

cloudflare/skills · 72 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens

story-origin-check

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

elvisun/newsjack · 40 tokens

annotating-task-lineage

Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.

astronomer/agents · 51 tokens

prompt-proximity-architecture

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…

elvisun/newsjack · 67 tokens

relevance-coarse-filter

Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.

elvisun/newsjack · 57 tokens