git-commit-conventional-strict

git-commit-conventional-strict is a skill for Claude Code, Codex from jamesyang124/agent-skills. It costs 57 tokens per session (2,374 once invoked), scanned A, original, MIT.

A guide for writing strict Conventional Commits, a structured format for git commit messages that tools can read to determine change types and releases. It also covers Semantic Versioning, which uses version numbers to communicate compatibility changes, and optional emoji conventions.

In plain words
What is it for?
Use it when deriving a commit message from the current git diff, adding a Jira ticket, or preparing commits for git-cliff and SemVer-based releases.
Why use it?
It reduces inconsistent commit messages and helps release-note and versioning tools interpret changes correctly.

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/jamesyang124/agent-skills/git-commit-conventional-strict
Any agent
npx skills add jamesyang124/agent-skills --skill git-commit-conventional-strict
Clone the repo
git clone --depth 1 https://github.com/jamesyang124/agent-skills

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 git-commit-conventional-strict

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesyang124/agent-skills/git-commit-conventional-strict.svg)](https://agentmods.dev/skills/jamesyang124/agent-skills/git-commit-conventional-strict)
Your own site
<a href="https://agentmods.dev/skills/jamesyang124/agent-skills/git-commit-conventional-strict"><img src="https://agentmods.dev/badge/skills/jamesyang124/agent-skills/git-commit-conventional-strict.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,374 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 $0.00057 $0.02374
Opus 5 $0.00028 $0.01187
Sonnet 5 $0.00011 $0.00475
Haiku 4.5 $0.00006 $0.00237

Measured 3d ago against content hash 83e83416fa07, 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-conventional-strict 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 3d 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.

.agent-settings/skills/tools/git-commit-conventional-strict/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Generator (Cliff Optimized)

Install this skill globally

Install once — available in all projects.

# Claude
mkdir -p ~/.claude/skills/git-commit-conventional-strict
cp <agent-settings-repo>/.agent-settings/skills/tools/git-commit-conventional-strict/SKILL.md \
   ~/.claude/skills/git-commit-conventional-strict/SKILL.md
# Add to ~/.claude/CLAUDE.md: - **git-commit-conventional-strict** (`~/.claude/skills/git-commit-conventional-strict/SKILL.md`)

# Copilot
mkdir -p ~/.copilot/skills/git-commit-conventional-strict
cp <agent-settings-repo>/.agent-settings/skills/tools/git-commit-conventional-strict/SKILL.md \
   ~/.copilot/skills/git-commit-conventional-strict/SKILL.md

You are an expert in Semantic Versioning (SemVer) and Conventional Commits. Your goal is to generate git commit messages that are machine-readable for tools like git-cliff while remaining human-readable.

Arguments

All optional. The message itself is always derived from the current git diff.

Token shape Interpreted as
matches [A-Z]+-\d+ Jira ticket ID — skips the step 5 prompt and goes straight into the subject line as type(scope): emoji [TICKET-ID] description
no / none / skip / n commit with no ticket — skips the step 5 prompt
anything else scope override (e.g. auth, ui, deps) instead of the scope inferred from the diff

No ticket token → step 5 asks for one.


Core Rules

  1. Structure:

    • Default: type(scope): emoji subject
    • Breaking Change: type(scope)!: emoji subject
    • Note: Scope is optional but recommended.
    • Keep messages simple and avoid special shell characters in examples
  2. Types & SemVer Mapping: Select the type based on the nature of the change and its impact on Semantic Versioning:

    • Major (💥 BREAKING CHANGE):
      • Syntax: Add exclamation mark after the type/scope (e.g., feat!:, fix(api)!:)
      • Use when the change breaks backward compatibility.
    • Minor (feat):
      • feat: A new feature.
    • Patch (fix):
      • fix: A bug fix.
    • No Version Bump (General):
      • docs: Documentation only changes.
      • style: Formatting, missing semi-colons, etc (no code change).
      • refactor: A code change that neither fixes a bug nor adds a feature.
      • perf: A code change that improves performance.
      • test: Adding missing tests or correcting existing tests.
      • build: Changes that affect the build system or external dependencies.
      • ci: Changes to CI configuration files and scripts.
      • chore: Other changes that don't modify src or test files.

Read the full file on GitHub · 209 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. 3d ago First seen · 209 lines · 57 tokens per session scan A 83e83416fa07

Subscribe to this mod's changes

git-commit-conventional-strict is a skill published in the GitHub repository jamesyang124/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,374 once invoked, about $0.0003 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.