git

git is a skill for Claude Code from gullitmiranda/.cursor. It costs 47 tokens per session (2,084 once invoked), scanned A, original, MIT.

A set of rules for carrying out Git version-control tasks safely and consistently.

In plain words
What is it for?
Use it when checking multiple repositories, creating branches, committing changes, resetting with a backup, or preparing conventional commits.
Why use it?
It reduces the risk of working on the wrong branch, losing changes during a reset, or creating unclear commit history.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it when checking multiple repositories, creating branches, committing changes, resetting with a backup, or preparing conventional commits.

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

Made for: Claude Code.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gullitmiranda/.cursor/git"><img src="https://agentmods.dev/badge/skills/gullitmiranda/.cursor/git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,084 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 $0.00047 $0.02084
Opus 5.5 $0.00019 $0.00834
Sonnet 5.5 $0.00009 $0.00417
Haiku 4.5 $0.00005 $0.00208

Measured 1mo ago against content hash acfccc78bd88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git 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 1mo 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.

skills/git/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/commit - Smart Git Commit

Overview

You are a git commit specialist that creates conventional commits with automatic type detection and safety checks.

Steps

  1. Branch Safety Check:

    • Check if currently on main/master branch
    • If yes and using /commit (without --main flag), automatically create a feature branch based on the changes detected
    • If using /commit --main, allow direct commit to main/master branch (emergency fixes only)
  2. Analyze Changes:

    • Run git status and git diff --cached (or git diff for all changes if --all flag is used)
    • Detect conventional commit type from changes:
      • feat: New features, components, functionality
      • fix: Bug fixes, error corrections
      • chore: Dependencies, build, config, tooling
      • docs: Documentation changes
      • style: Code formatting, style changes
      • refactor: Code restructuring without behavior change
      • test: Adding or updating tests
    • Check for Linear issue references in commit message or staged changes
  3. Generate Commit Message:

    • Format: <type>(<scope>): <description>
    • Scope should be component/area affected (optional)
    • Description should be concise and clear
    • Use present tense, imperative mood
    • Include Linear issue references (e.g., ENG-123, PROJ-456) in description for auto-linking
  4. Execute Commit:

    • Use heredoc format for multi-line commit messages
    • Commit only staged changes (unless --all flag is used)
    • If --all flag is used, stage and commit all changes (unstaged + staged)
    • Confirm successful commit with git log
  5. Validation:

    • Ensure commit follows conventional format
    • Verify only intended changes were committed

Auto Branch Creation

When on main/master branch and using /commit (without --main flag):

  1. Analyze Changes: Detect commit type from staged/unstaged changes
  2. Generate Branch Name:
    • For features: feature/<type>-<short-description>
    • For fixes: fix/<short-description>
    • For chores: chore/<short-description>
    • For docs: docs/<short-description>
  3. Create Branch: git checkout -b <generated-branch-name>
  4. Proceed with Commit: Continue with normal commit process

Read the full file on GitHub · 334 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. 1mo ago First seen · 334 lines · 47 tokens per session scan A acfccc78bd88

Subscribe to this mod's changes

git is a skill published in the GitHub repository gullitmiranda/.cursor (2 stars, last pushed 8mo ago), licensed MIT. It adds 47 tokens to every session and 2,084 once invoked, about $0.0002 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 2026-08-31.