git-commits

git-commits is a skill for Claude Code, Codex from ErikaAX08/erikas-skills. It costs 102 tokens per session (5,608 once invoked), scanned A, original, MIT.

A git-writing skill for clear commit messages and pull- or merge-request titles using Conventional Commits, a common format that labels the kind of change.

In plain words
What is it for?
Use it to decide whether changes belong in one or several commits and to write suitable commit messages, merge messages, or pull-request titles.
Why use it?
It makes project history easier to search, understand, and automate by avoiding vague messages and mixing unrelated changes. Repository-specific rules take priority.

Skill for Claude CodeCodex

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

Good fit Use it to decide whether changes belong in one or several commits and to write suitable commit messages, merge messages, or pull-request titles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erikaax08/erikas-skills/git-commits
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 ErikaAX08/erikas-skills --skill git-commits
Clone the repo
git clone --depth 1 https://github.com/ErikaAX08/erikas-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-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/erikaax08/erikas-skills/git-commits/github.svg)](https://agentmods.dev/skills/erikaax08/erikas-skills/git-commits)
Your own site
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/git-commits"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/git-commits/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 git-commits

Your own site · 80×15
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/git-commits"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/git-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,608 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 $0.00102 $0.05608
Opus 5 $0.00051 $0.02804
Sonnet 5 $0.00020 $0.01122
Haiku 4.5 $0.00010 $0.00561

Measured 10d ago against content hash f6f90bd4ad07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

git-commits 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 10d 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.

git-commits/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GIT-COMMITS.md — Conventional Commits Engineering Skill

Purpose: this is the operational rulebook an AI agent (or a human) follows to write commit messages, PR/MR titles, and merge messages that make project history easy to read, bisect, and automate against — without the vagueness, mixed concerns, and inconsistency that make git history useless six months later. The full PR/MR body description is the create-pull-request skill's job — this file only owns the title format it shares with that skill.

This file is self-contained by design. It doesn't assume access to any specific repo's own CONTRIBUTING.md or commit conventions. If the target repo has its own documented commit conventions, those win over this file wherever they conflict — this file is the default, not an override.


0. How to use this file

  1. Before writing a commit message, identify: is this one logical change or several unrelated ones? Use §6 ("Multiple Related vs. Unrelated Changes") to decide whether to split into multiple commits before drafting any message.
  2. While drafting, follow §2–§4 for type, scope, description, body, and footer. Check §1's non-negotiables first — they catch the mistakes that are easiest to make on autopilot.
  3. For anything other than a plain new commit (a revert, a merge, an amend, a squash, a hotfix, a dependency bump), check §5 — these have their own shape and their own rules about what's safe to rewrite.
  4. Before opening a PR, use §7 for the PR/MR title format and §8 for real scenario examples. For the PR/MR body, use the create-pull-request skill instead.
  5. Before delivering the final message, run it through §10 (quality checklist) and follow §11's delivery rules for where the result goes (file vs. terminal).
  6. If the user's repo has its own commit convention that conflicts with this file, the repo's own convention wins — treat this file as the default for repos with no stated convention of their own, not as an override.

Read the full file on GitHub · 597 lines

Files

What ships with it

1 file 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. 10d ago First seen · 597 lines · 102 tokens per session scan A f6f90bd4ad07

Subscribe to this mod's changes

git-commits is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed 11d ago), licensed MIT. It adds 102 tokens to every session and 5,608 once invoked, about $0.0005 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.