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/anthonyposchen/agent-skills/git-commit-workflownpx skills add AnthonyPoschen/agent-skills --skill git-commit-workflowgit clone --depth 1 https://github.com/AnthonyPoschen/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 | $0.00084 | $0.01237 |
| Opus 5 | $0.00042 | $0.00619 |
| Sonnet 5 | $0.00017 | $0.00247 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
git-commit-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 yesterday.
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Workflow
Goal
Create small, reviewable commits with clear, descriptive subjects and an explicit AI assistance trailer. Always separate independent logical units of work into separate commits. Prefer preserving user changes over making a tidy history at the cost of mixing unrelated work.
When To Commit
- When the user asks to commit, stage, split commits, or push as part of finishing work.
- When a loaded skill or reference completes a phase of sequenced work and the tree changed. Treat that as authorization. Commit the phase, then continue the next phase without waiting for a separate commit prompt.
Safety Rules
- Never discard, reset, restore, clean, or overwrite user changes unless the user explicitly asks for that destructive action.
- Inspect the worktree before staging:
git status --short, then targeted diffs for changed files. - Stage only files that belong to the commit being made.
- Treat already-staged changes as provisional, not authoritative. Inspect the staged diff and unstage/re-stage by logical unit when staged content contains multiple independent concerns.
- If unrelated changes exist, leave them unstaged and mention them.
- If a file contains changes from multiple concerns, use an interactive or patch-based staging flow when available. If not practical, ask before mixing concerns.
- Do not amend, rebase, squash, or rewrite commits unless the user asks.
Commit Splitting
Split commits when their changes can be reviewed, validated, and reverted independently. Keep changes together when splitting would leave either commit incomplete or broken.
If the staged area or worktree contains multiple independent features, bug fixes, refactors, documentation changes, dependency updates, generated output, formatting, or infrastructure changes, create separate commits.
Each commit should represent one coherent unit of work that can be understood, reviewed, reverted, and tested on its own. Common split points:
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.
- yesterday First seen · 149 lines · 84 tokens per session scan A 067aa12d96a6
git-commit-workflow is a skill published in the GitHub repository AnthonyPoschen/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,237 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…