agentmods.dev

git-commit

git-commit is a skill for Claude Code, Codex from saajunaid/caddis-plugin. It costs 32 tokens per session (1,664 once invoked), scanned A, original, MIT.

A helper for writing Git commit messages in the Conventional Commits format. That format labels changes consistently, such as features, fixes, or documentation updates.

In plain words
What is it for?
Use it when committing work, preparing pull requests, or generating changelogs.
Why use it?
It makes commit history easier to scan and gives tools a predictable way to group changes or create changelogs.

Skill for Claude CodeCodex

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

not rated 0repo changed 19d ago A scan 32 tokens original MIT

Good fit Use it when committing work, preparing pull requests, or generating changelogs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saajunaid/caddis-plugin/git-commit
View source ↗ saajunaid/caddis-plugin saajunaid.github.io
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 saajunaid/caddis-plugin --skill git-commit
Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/git-commit"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/git-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,664 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 $0.00032 $0.01664
Opus 5.5 $0.00013 $0.00666
Sonnet 5.5 $0.00006 $0.00333
Haiku 4.5 $0.00003 $0.00166

Measured 19d ago against content hash ceaf59ad6f3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-commit 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 19d 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.

.github/skills/devops/git-commit/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Skill

Create meaningful, conventional commit messages that follow team standards.

Trigger

Activate when:

  • User asks to commit changes
  • User needs help writing a commit message
  • User asks "what should I commit this as?"

Conventional Commit Format

<type>(<scope>): <subject>

[optional body]

[optional footer]

Types

Type Description Example
feat New feature feat(complaints): add priority filtering
fix Bug fix fix(auth): resolve session timeout issue
docs Documentation docs: update API documentation
style Formatting (no code change) style: fix indentation in models
refactor Code restructuring refactor(db): extract query builder
perf Performance improvement perf: add caching to dashboard
test Adding/fixing tests test: add complaint service tests
chore Maintenance chore: update dependencies
ci CI/CD changes ci: add pytest to GitHub Actions
build Build system/dependencies build: update webpack to v5
revert Revert a previous commit revert: revert feat(api) endpoint

Scope

Optional area of change:

  • api - Backend API changes
  • ui - Frontend/Streamlit changes
  • db - Database changes
  • auth - Authentication
  • complaints - Complaints feature
  • analytics - Analytics feature

Phase 1: Analyze Changes

Actions

  1. Run a pre-commit quality gate (blocking)

    # Python repos
ruff check .

# TypeScript/React repos
npm run lint

# If both stacks exist, run both.

    If lint fails, do not proceed to commit generation until fixed.

  2. Review staged changes

    # If files are staged, use staged diff
git diff --staged --stat
git diff --staged

# If nothing staged, check working tree
git diff
git status --porcelain

  3. Stage files if needed

    # Stage specific files
git add path/to/file1 path/to/file2

# Never stage by pattern or folder (`*.test.*`, `src/components/`): a pattern also takes
# files you did not change, and the caddis guard denies it. Name each file.

Read the full file on GitHub · 284 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. 19d ago Changed · -1 lines ceaf59ad6f3a
  2. 2mo ago First seen · 285 lines · 32 tokens per session scan A 5607ee79697d

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,664 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

CommitsGit and workflowagent-frameworkagentic-aiagentic-automationagentic-workflowai-agentsautomation
Related

git-commit compared with skills from other repositories

git-commit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-commitsaajunaid/caddis-pluginSkill0yesterdayMITA32Claude Code, Codex
commitcongchuanling-dot/CohortSkill1882mo agoMITA59Claude Code
agentic-jujutsuruvnet/rufloSkill81kyesterdayMITA26Claude Code
github-automationruvnet/rufloSkill81kyesterdayMITA61Claude Code
git-integrationa5c-ai/babysitterSkill1.9k5d agoMITA39Claude Code
audit-traila5c-ai/babysitterSkill1.9k5d agoMITA0Claude Code, Codex
moai-ref-git-workflowmodu-ai/moai-adkSkill1.3k4d agoApache-2.0A58Claude Code