A single command interface for common Git tasks, where Git is the version-control system used to track code changes.

Use it to create commits, open normal or draft pull requests, and begin work on a GitHub issue by number or title.

It avoids having separate workflows for routine repository work such as committing changes, opening pull requests, and starting issue work.

git — Command by stefan-jansen

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 commands/stefan-jansen/claude-code-toolkit/git

Clone the repo

git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 855 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00855
Opus 5	$0.00006	$0.00428
Sonnet 5	$0.00002	$0.00171
Haiku 4.5	$0.00001	$0.00085

Measured yesterday against content hash a06c5a44ec31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

plugins/development/commands/git.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Operations Hub

Consolidated command for all git-related operations. Combines commit, PR, and issue workflows into a single interface.

Input: $ARGUMENTS

Usage

Commit Operations

/git commit "feat: Add user authentication"
/git commit                               # Interactive commit message

Pull Request Operations

/git pr                                   # Create PR from current branch
/git pr --draft                          # Create draft PR

Issue Operations

/git issue "#123"                         # Start work on GitHub issue
/git issue "Fix login bug"               # Work on issue by title

Phase 1: Parse Operation Type

Based on the arguments provided: $ARGUMENTS

I'll determine which git operation to perform:

If arguments start with "commit": Handle git commit workflow
If arguments start with "pr": Handle pull request creation
If arguments start with "issue": Handle GitHub issue workflow
If no arguments: Show usage help

Phase 2: Execute Git Commit Workflow

When handling commit operations:

Pre-Commit Validation

Check git status to see what files are staged/modified
Ensure we're in a git repository
Validate that there are changes to commit

Quality Gates

Run available tests (if any exist)
Check for linting issues (if tools available)
Verify no secrets or sensitive data being committed

Commit Creation

Stage appropriate files if needed
Generate conventional commit message if not provided
Execute git commit with proper formatting
Include Claude Code attribution

Phase 3: Execute Pull Request Workflow

When handling PR operations:

Pre-PR Validation

Ensure we're on a feature branch (not main/master)
Check that commits exist beyond main branch
Verify branch is pushed to remote

PR Creation

Use GitHub CLI (gh) if available
Generate meaningful PR title and description
Include summary of changes made
Link to relevant issues if applicable
Set appropriate labels and reviewers

Read the full file on GitHub · 149 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.

yesterday First seen · 149 lines · 12 tokens per session scan A a06c5a44ec31

Subscribe to this mod's changes

git is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 855 once invoked, about $0.0001 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 2026-08-30.

Git and workflow agents anthropic claude-code coding-agents framework plugins

git