git-workflow

A set of rules for using Git, the tool that records and shares code changes, safely. It covers inspecting existing work, keeping changes focused, and creating clear history when requested.

In plain words
What is it for?
Use it before editing, branching, staging, committing, or preparing a pull request, while preserving work that was already in the repository.
Why use it?
It helps prevent accidental overwrites, unrelated edits, leaked secrets, and confusing change sets.

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/extra-org/extra/git-workflow
Any agent
npx skills add extra-org/extra --skill git-workflow
Clone the repo
git clone --depth 1 https://github.com/extra-org/extra

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 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 $0.00038 $0.00748
Opus 5 $0.00019 $0.00374
Sonnet 5 $0.00008 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 2d ago against content hash 10ef9f9fc1ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-workflow 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.

.claude/skills/git-workflow/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Git Workflow

Purpose

Work safely with Git: keep changes scoped and reviewable, never overwrite the user's work, and produce clear history.

When to Use This Skill

  • Before editing files (inspect current state first).
  • Branching, staging, or committing.
  • Preparing a change set or pull request for review.

Files to Read First

  • AGENTS.md (git safety + scope rules).
  • docs/DEVELOPMENT_WORKFLOW.md.
  • The current diff/status of the repository.

Core Principles

  • Inspect before editing. Run git status and git diff to understand uncommitted work; never clobber the user's changes.
  • Keep changes scoped to one task; avoid massive unrelated diffs.
  • Don't reformat or move files outside scope.
  • Commit only when asked. Do not auto-commit; never force-push shared branches or skip hooks.
  • Clear messages. Use a conventional, scoped commit style.
  • No secrets. Never stage .env, credentials, or large binaries.

Process

  1. Inspect: git status and git diff (and git log --oneline -5 for message style). Note any pre-existing uncommitted work to preserve.
  2. Scope the change to the current task; keep unrelated edits out.
  3. Stage deliberately (git add <paths>) — review what's staged; ensure no secrets or ignored files sneak in.
  4. Commit when asked, using the format below and a HEREDOC for the message.
  5. Summarize the modified files in your final response.

Commit message format

Use a conventional prefix:

  • feat: a new feature/capability
  • fix: a bug fix
  • refactor: behavior-preserving restructuring
  • docs: documentation only
  • test: tests only
  • chore: tooling/config/housekeeping

Example: docs: consolidate agent instructions under .ai/

Checklist Before Finishing

  • Inspected git status/git diff before editing; no user work clobbered.
  • Change is scoped to one task; no unrelated churn.
  • No secrets, .env, or large binaries staged.
  • Commit message (if committing) uses the conventional format.
  • Only committed because the user asked.
  • Modified files summarized in the final response.

Read the full file on GitHub · 89 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 · 89 lines · 38 tokens per session scan A 10ef9f9fc1ab

Subscribe to this mod's changes

git-workflow is a skill published in the GitHub repository extra-org/extra (108 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 748 once invoked, about $0.0002 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.