git

A guide to common Git version-control workflows. Git records changes to code so developers can work in branches, combine changes, and review project history.

In plain words
What is it for?
Use it when creating commits or branches, opening or merging pull requests, rebasing, squashing, cherry-picking, or resolving conflicts.
Why use it?
It helps choose consistent commit messages and safer approaches for branches, pull requests, history editing, and merge conflicts.

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

Made for: Claude Code, Codex.

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,497 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 $0.00132 $0.03497
Opus 5 $0.00066 $0.01749
Sonnet 5 $0.00026 $0.00699
Haiku 4.5 $0.00013 $0.00350

Measured 2d ago against content hash 39ad99dfe164, 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.

skills/git/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git

Git 버전 관리 모범 관례 및 워크플로우 가이드.

커밋 메시지 컨벤션

Conventional Commits 사용

커밋 메시지는 <type>: <description> 형식을 따른다:

feat: add form validation to login page
fix: prevent duplicate email check error on signup
docs: add installation guide to README
refactor: extract auth logic into separate module
test: add payment feature tests
chore: update dependencies
주요 타입
타입 설명 예시
feat 새로운 기능 추가 feat: add dark mode support
fix 버그 수정 fix: prevent token deletion on logout
docs 문서 변경 (코드 변경 없음) docs: update API documentation
style 코드 포맷팅, 세미콜론 누락 (동작 변경 X) style: apply ESLint rules
refactor 리팩토링 (기능 변경 없음) refactor: extract utility functions
test 테스트 코드 추가/수정 test: add login API tests
chore 빌드, 설정 변경 (src 변경 없음) chore: update Webpack config
perf 성능 개선 perf: implement lazy loading for images
상세 형식 (선택사항)
<type>(<scope>): <subject>

<body>

<footer>

예시:

feat(auth): implement JWT-based authentication

- Issue access and refresh tokens
- Store refresh tokens in Redis
- Add token renewal API endpoint

Closes #123
자주 하는 실수
# ❌ 타입 누락
git commit -m "bug fix"

# ❌ 모호한 설명
git commit -m "fix: fix issue"

# ❌ 한 커밋에 여러 작업
git commit -m "feat: implement login, signup, and password reset"

# ✅ 명확하고 단일 책임
git commit -m "feat: add form validation to login page"

커밋 메시지 작성 가이드라인

  1. 첫 줄은 50자 이내 - 간결한 요약
  2. 현재형 사용 - "added" (X) → "add" (O)
  3. 명령형 어조 - "adds" (X) → "add" (O)
  4. 첫 글자 소문자 - Feat: (X) → feat: (O)
  5. 마침표 금지 - feat: add feature. (X) → feat: add feature (O)
  6. 본문은 72자마다 줄바꿈 - 가독성 향상
  7. Why > What - 변경한 내용보다 변경한 이유를 설명
  8. 영어로 작성 - 릴리즈 노트 생성 도구와의 호환성을 위해

Read the full file on GitHub · 478 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 · 478 lines · 132 tokens per session scan A 39ad99dfe164

Subscribe to this mod's changes

git is a skill published in the GitHub repository DaleStudy/skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session and 3,497 once invoked, about $0.0007 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 2026-08-31.