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.
npx agentmods add skills/developersglobal/ai-agent-skills/git-workflownpx skills add DevelopersGlobal/ai-agent-skills --skill git-workflowgit clone --depth 1 https://github.com/DevelopersGlobal/ai-agent-skillsWhat 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 | $0.00027 | $0.00650 |
| Opus 5 | $0.00014 | $0.00325 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Git is not just a backup system — it's a communication tool. Clean git history enables fast debugging (git bisect), clear attribution, and safe reverts. This skill enforces atomic commits, meaningful messages, and trunk-based development.
When to Use
- Before making any commit
- When reviewing a PR's git history
- When setting up a new project
Process
Step 1: Atomic Commits
- Each commit should represent ONE logical change — not a day's worth of work.
- A commit should be: independently deployable, independently revertable.
- Never commit "WIP" or partial implementations.
Verify: You could revert this commit without affecting adjacent functionality.
Step 2: Commit Message Format
- Follow Conventional Commits:
type(scope): short summary (max 72 chars) Body: what changed and WHY (not how — the diff shows how). Closes: #issue-number - Types:
feat,fix,docs,style,refactor,test,chore - The summary is imperative mood: "Add feature" not "Added feature"
Verify: Message passes: feat|fix|docs|...(<scope>): <summary> format.
Step 3: Trunk-Based Development
- Work directly on
mainfor small changes (<1 day of work). - For larger features: short-lived feature branches (max 2 days), frequent merges to main.
- Never let a branch live more than 3 days without merging or rebasing.
- Use feature flags for incomplete features, not long-lived branches.
Verify: No branch is more than 2 days old without a merge/rebase plan.
Step 4: Pre-Commit Gates
- Before every commit: tests pass, linter passes, no secrets in diff.
- Use pre-commit hooks to enforce automatically.
Common Rationalizations (and Rebuttals)
| Excuse | Rebuttal |
|---|---|
| "I'll clean up the commits later" | You won't. Clean as you go. |
| "The commit message doesn't matter" | It matters in 6 months when you're bisecting a production bug. |
| "Feature branches protect main" | Long-lived branches cause merge nightmares. Trunk-based is safer. |
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.
- 3d ago First seen · 77 lines · 27 tokens per session scan A ad9c6433f8df
git-workflow is a skill published in the GitHub repository DevelopersGlobal/ai-agent-skills (65 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 650 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.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests. Use when user asks to "add pre-commit hooks", "setup husky", "setup pre-commit", "configure lint-staged", or wants commit-time formatting/typechecking/testing. Don't use for running linters manually or writing tests.
commit
Group unstaged changes into atomic commits by concern, following repository style. Use when user asks to "commit", "create a commit", "commit changes", or "/commit". Don't use for pushing (that belongs to /ship) or creating pull requests.
ship
Commit and push changes with a pre-launch gate (validate-code + safe-repo) by default. --fast skips the gate.
git-workflow-and-versioning
规范 git 工作流实践。用于进行任何代码变更时；用于提交、分支、解决冲突，或需要组织多个并行工作流时。.
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.