git-commit

An automated workflow for committing code changes to Git, a system that records versions of files.

In plain words
What is it for?
Use it when you want to commit finished work with a generated Conventional Commit message and the project's required memory updates.
Why use it?
It organizes the commit process, including reviewing changes, writing a standard commit message, updating project memory, and adding a tag.

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

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,411 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 $0.00087 $0.01411
Opus 5 $0.00044 $0.00705
Sonnet 5 $0.00017 $0.00282
Haiku 4.5 $0.00009 $0.00141

Measured yesterday against content hash e8e182a26d99, 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 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/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit

Overview

This skill automates the complete git commit workflow: analyze changes, generate an English Conventional Commit message in the required <type>: AI <subject> format, update project memory, stage, commit, and tag.

Workflow

Execute the following steps in order when this skill is invoked:

Step 1: Analyze Conversation Context

Review the conversation history to understand:

  • What code changes were made
  • What features were added or bugs were fixed
  • What architectural decisions or design choices were discussed
  • What files were modified or created

Step 2: Check Git Status

Run parallel git commands to gather current repository state:

# Check untracked and modified files (never use -uall flag)
git status

# View staged and unstaged changes
git diff HEAD

# View recent commit messages to understand the project's commit style
git log --oneline -10

Step 3: Generate Commit Message

Based on the analysis, generate a commit message following Conventional Commits format.

Format:

<type>: AI <subject>

<body>

Co-Authored-By: AI Coding Agent <[email protected]>

Type options:

  • build: Build system or dependencies changes
  • chore: Maintenance work that does not fit other types
  • ci: CI/CD changes
  • docs: Documentation changes
  • feat: New feature
  • fix: Bug fix
  • perf: Performance improvements
  • refactor: Code refactoring without behavior change
  • revert: Revert a previous change
  • style: Formatting or style-only changes with no logic impact
  • test: Adding or updating tests

Guidelines:

  • Always use one of the allowed types above; do not invent new types
  • Do not add a scope; the prefix must stay exactly <type>: AI
  • Subject: Concise summary (50-72 chars max), imperative mood, no period, written in English
  • Body: When needed, explain what changed and why in English, including key implementation details and impact on the codebase
  • Keep each line in body under 72 characters
  • Use blank line between subject and body
  • Example: feat: AI user login

Read the full file on GitHub · 162 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 · 162 lines · 87 tokens per session scan A e8e182a26d99

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository wufunc/nova (2 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,411 once invoked, about $0.0004 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.