git-best-practices

A set of Git guidelines for creating commits, managing branches, opening pull requests, and rewriting project history. Git is the version-control system used to track code changes.

In plain words
What is it for?
Inspecting repository state, discovering important branches, staging selected files, creating conventional commits, pushing changes safely, and making temporary checkpoint commits during longer tasks.
Why use it?
It reduces accidental commits, unsafe force-pushes, and confusion about which branches are shared or production-critical. It also encourages consistent commit messages and checking the repository before acting.

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/alleneubank/claude-code/git-best-practices
Any agent
npx skills add alleneubank/claude-code --skill git-best-practices
Clone the repo
git clone --depth 1 https://github.com/alleneubank/claude-code

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,519 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 $0.00036 $0.01519
Opus 5 $0.00018 $0.00759
Sonnet 5 $0.00007 $0.00304
Haiku 4.5 $0.00004 $0.00152

Measured 2d ago against content hash aa1173edbbbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-best-practices 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-best-practices/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Best Practices

Always Active Principles

When this skill is loaded, follow these directives for all git operations:

  1. Discover before acting — run branch discovery to determine the repo's default and production branches before branching, merging, or opening PRs
  2. Conventional commits — every commit uses type(scope): description format
  3. Stage explicitly — add files by name so only intended changes are committed
  4. Protect shared history — use --force-with-lease for force pushes; confirm with the user before any force push

Agent Git Workflow

  1. Check state — run git status and git diff HEAD
  2. Discover branches — identify default/current/(optional) production branch names (see Branch Discovery)
  3. Stage by namegit add path/to/file for each file; verify with git status
  4. Write a conventional committype(scope): description with optional body
  5. Push safely — regular push by default; git push --force-with-lease origin {branch} only for rewritten history after user confirmation

Checkpoint Commits

Agents may create WIP checkpoint commits during long-running tasks, cleaned up before PR.

  • Prefix with wip: or use standard conventional commit format
  • Keep changes logically grouped even in WIP state
  • Run /rewrite-history before opening a PR to craft a clean narrative

Commit Discipline

  • Stage files explicitly by name: git add src/auth.ts src/auth.test.ts
  • Verify staged content with git status before committing
  • Keep secrets, .env files, credentials, and large binaries out of commits — warn the user if staged files look sensitive
  • Target one logical change per commit in final PR-ready state

Force Push

Use --force-with-lease exclusively to protect against overwriting upstream changes:

git push --force-with-lease origin feat/my-branch

Always confirm with the user before any force push, regardless of branch.

Rebasing a Stack

When rebasing a branch that other branches are stacked on (e.g. phased NN-description chains), use git rebase --update-refs so the stacked branches follow the rewrite instead of being orphaned on the old commits. --update-refs moves local refs only — each moved branch that also exists on the remote still needs its own --force-with-lease push (after confirmation), and any branch checked out in another worktree is skipped. For the full conflict-resolution and safety workflow, use the git-rebase-sync skill.

Read the full file on GitHub · 175 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 175 lines · 36 tokens per session scan A aa1173edbbbe

Subscribe to this mod's changes

git-best-practices is a skill published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,519 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens