dev-git-commit-message

A Conventional Commits assistant for creating or checking commit messages from staged code changes. Conventional Commits is a shared format such as `fix(scope): summary` that makes changes easier to understand and automate.

In plain words
What is it for?
Use it to draft or validate commit messages, decide when to include a body or breaking-change marker, and follow repository-specific commit rules.
Why use it?
It helps choose an appropriate commit type and scope while avoiding claims that are not visible in the staged changes.

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/vasilyu1983/ai-agents-public/dev-git-commit-message
Any agent
npx skills add vasilyu1983/AI-Agents-public --skill dev-git-commit-message
Clone the repo
git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-public

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,196 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 $0.00038 $0.03196
Opus 5 $0.00019 $0.01598
Sonnet 5 $0.00008 $0.00639
Haiku 4.5 $0.00004 $0.00320

Measured 2d ago against content hash edb7f3a50187, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/commit_validator.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

frameworks/shared-skills/skills/dev-git-commit-message/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Message Generator

Generate or validate Conventional Commits for the staged surface.

Default posture: subject line first; body only when risk, rationale, or breaking-change detail is needed; standard types only unless the repo already defines custom ones; never claim behavior not visible in the diff.

Quick Reference

Need Default Reference
Pick a type feat/fix/perf/refactor/docs/test/build/ci/chore/style/revert Type Selection table below
Format a subject type(scope): imperative summary, ≤72 chars (50 ideal), no trailing period Pre-Commit Message Checklist below
Mark a breaking change ! after type/scope, or a BREAKING CHANGE: footer Breaking Change Format table below
Decide on a body Only for risk, non-obvious rationale, or breaking-change detail Body Required? table below
Handle AI-authored commits No tool attribution ever; Assisted-by: trailer only if the repo opts in AI-Authored Commits below
Pick a release/changelog tool release-please for reviewed PR releases; semantic-release for full automation; changesets for monorepos references/changelog-generation-guide.md
Scope a monorepo commit package/app/service directory name, one level deep, stable over time references/monorepo-commit-conventions.md
Validate a message locally python scripts/commit_validator.py validate --message "..." Scripts section below

Decision Tables

Mode Selection

Trigger Mode Action
User provides staged diff or asks to commit Generate Inspect staged surface, produce primary + alternatives
User provides an existing message string Validate Check rules, return PASS/WARN/FAIL + exact rewrite
Staged diff mixes unrelated areas Split Recommend split commits before generating
No staged changes Stop Report "no staged changes"

Read the full file on GitHub · 266 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. 2d ago First seen · 266 lines · 38 tokens per session scan A edb7f3a50187

Subscribe to this mod's changes

dev-git-commit-message is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (82 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 3,196 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 2026-08-30.