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/kid-sid/codex-spellbook/git-workflownpx skills add kid-sid/codex-spellbook --skill git-workflowgit clone --depth 1 https://github.com/kid-sid/codex-spellbookWhat 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 | $0.00039 | $0.00660 |
| Opus 5 | $0.00019 | $0.00330 |
| Sonnet 5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Keep history readable, reviewable, and safe for collaborators by using consistent branch names, conventional commits, and disciplined merge behavior.
When to Activate
- Start a new feature or fix branch
- Prepare commits before opening a PR
- Rename a noisy branch before review
- Decide whether to squash or merge
- Rewrite branch history after review feedback
- Audit commit hygiene before release
- Recover from a mistaken push safely
Branch Naming
| Change Type | Pattern | Example |
|---|---|---|
| Feature | feat/<topic> |
feat/api-pagination |
| Fix | fix/<topic> |
fix/jwt-expiry-check |
| Chore | chore/<topic> |
chore/update-ci |
Conventional Commits
| Type | Use When |
|---|---|
feat: |
User-visible capability added |
fix: |
Bug fixed |
docs: |
Documentation only |
chore: |
Maintenance with no product behavior change |
refactor: |
Structure changed without behavior change |
test: |
Tests added or updated |
perf: |
Measurable performance improvement |
feat(api): add cursor pagination to list users
Why:
- offset scans were timing out on large tenants
What:
- added cursor token parsing
- exposed page.has_more
Pull Requests and Merge Strategy
| Field | Format |
|---|---|
| PR title | <type>(<scope>): <summary> |
| Description | problem, approach, risks, validation |
| Linked work | issue or ticket reference when available |
| Situation | Preferred | Avoid |
|---|---|---|
| Small feature branch | Squash merge | Preserving noisy fixup history |
| Multi-commit change with meaningful milestones | Merge commit | Squashing away useful audit trail |
| Local cleanup before review | Rebase locally | Rewriting shared branch unexpectedly |
Safe Rewrites
| Operation | Rule |
|---|---|
| Rewrite your own reviewed branch | Use --force-with-lease |
| Rewrite shared branch used by others | Do not do it without explicit coordination |
| Recover from mistaken push | Prefer revert when branch is public |
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.
- 2d ago First seen · 96 lines · 39 tokens per session scan A af446efab65a
git-workflow is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 660 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…