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/fmflurry/settings-opencode/git-workflownpx skills add fmflurry/settings-opencode --skill git-workflowgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat 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 | $0.00042 | $0.00997 |
| Opus 5 | $0.00021 | $0.00498 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
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 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow Skill
Use this skill whenever the task involves git.
When to Activate
- Creating or renaming branches
- Staging changes
- Writing commit messages
- Creating commits
- Pushing branches
- Preparing pull requests
- Reviewing branch names or commit message format
Required Delegation
When git work is needed, delegate to the dedicated git-specialist subagent via the /git command.
- Do not handle substantive git workflow directly in the main agent when
/gitcan handle it. - Use the
git-specialistagent for branch naming, commit message drafting, staging, commits, and pushes. - Keep non-git implementation work in the main agent, then switch to
/gitfor repository operations. - If you are already the
git-specialistagent, execute the git task directly and do not re-delegate it.
Commit Convention
Every commit message must follow this format:
<type>(<scope>): <short summary>
[optional body]
[optional footer(s)]
When scope is not useful or not clear, this no-scope form is also valid:
<type>: <short summary>
Allowed Types
feat: A new featurefix: A bug fixdocs: Documentation only changesstyle: Changes that do not affect behavior, such as formattingrefactor: Code changes that neither fix a bug nor add a featuretest: Adding or correcting testschore: Maintenance tasks such as tooling or build updates
Commit Rules
- Prefer including a meaningful
scopewhen the affected area is clear - Omit
scopeinstead of inventing one when it is not clear - Use a concise present-tense summary
- Keep the summary focused on intent, not a file-by-file changelog
- Match the type to the actual purpose of the change
Examples
feat(api): add user authentication endpointfix(auth): prevent empty login submissionchore(settings): sync opencode configuration
Branch Convention
Every branch name must follow this format:
<type>/<scope>-<short-description>
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 · 131 lines · 42 tokens per session scan A 2319ffe84791
git-workflow is a skill published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 19d ago), licensed MIT. It adds 42 tokens to every session and 997 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.
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…