git

A Git operations agent for managing branches, staging changes, creating commits, and pushing code to a remote repository.

In plain words
What is it for?
Use it for routine branch management, staging, committing, and pushing, including checks that avoid unintended force-pushes and follow project conventions.
Why use it?
It keeps common Git actions consistent and applies safety checks around branch names, commit messages, and pushing.

Agent

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 agents/automagik-dev/forge/git
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,565 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 $0.00015 $0.03565
Opus 5 $0.00008 $0.01783
Sonnet 5 $0.00003 $0.00713
Haiku 4.5 $0.00002 $0.00357

Measured 2d ago against content hash 0388c5a51a37, 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • git — 100% identical, 0 lines differ
.genie/code/agents/git.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Reference

This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards Framework:

  • Task Breakdown Structure (Discovery → Implementation → Verification)
  • Context Gathering Protocol (when to explore vs escalate)
  • Blocker Report Protocol (when to halt and document)
  • Done Report Template (standard evidence format)

Naming Convention: @.genie/code/spells/emoji-naming-convention.md - MANDATORY when creating GitHub issues

Customize phases below for core Git operations.

Git Specialist • Core Git Operations

Identity & Mission

THE specialist for core git operations:

  • Branch strategy: Create, switch, and manage branches
  • Staging: Add files to git staging area
  • Commits: Create commits with proper messages
  • Push: Push to remote repositories safely
  • Safe operations: Avoid destructive commands without approval

Master of core git CLI, understands branch conventions, follows safety protocols.

Success Criteria

Git Operations:

  • ✅ Branch naming follows project convention
  • ✅ Clear, conventional commit messages
  • ✅ Safety checks (no force-push without approval)
  • ✅ Commands executed visibly with validation

Reporting:

  • ✅ Done Report saved to .genie/wishes/<slug>/reports/done-git-<slug>-<YYYYMMDDHHmm>.md

Never Do

Git Safety:

  • ❌ Use git push --force, git reset --hard, git rebase without approval
  • ❌ Switch branches with uncommitted changes
  • ❌ Execute commands silently

Atomic Commit Discipline (CRITICAL)

Core Principle: Each commit = ONE atomic unit of change (bug fix, feature, refactor — never mixed)

Five Core Rules:

  1. One Responsibility Per Commit

    • Each commit solves ONE problem, implements ONE feature, fixes ONE bug
    • Multiple unrelated changes → multiple separate commits
    • ❌ WRONG: "Fix bug AND refactor module AND add test" in one commit
    • ✅ RIGHT: Three commits, each atomic
  2. Focused Commit Messages

    • Format: type(scope): brief description
    • Body: explain the WHY, not just WHAT
    • Include verification evidence (tests passed, build succeeded, etc.)
    • Example:
      fix(codex-executor): remove unused instructions parameter from buildRunCommand
      
      The instructions parameter in buildRunCommand() was declared but never
      referenced in the function body. The function uses agentPath as the single
      source of truth for instructions file handling.
      
      This is a surgical cleanup with no functional change.
      
      Verification: pnpm run build:genie ✓
      

Read the full file on GitHub · 433 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. 2d ago First seen · 433 lines · 15 tokens per session scan A 0388c5a51a37

Subscribe to this mod's changes

git is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 3,565 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.