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/development-workflownpx skills add kid-sid/codex-spellbook --skill development-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 | $0.00036 | $0.03087 |
| Opus 5 | $0.00018 | $0.01543 |
| Sonnet 5 | $0.00007 | $0.00617 |
| Haiku 4.5 | $0.00004 | $0.00309 |
Grade A, and why
development-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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
A complete reference for Git branching, commit conventions, pull request workflow, code review practices, and release management — covering everything from first branch to published release.
When to Activate
- Starting work on a new feature, bug fix, or chore
- Writing a commit message
- Opening or reviewing a pull request
- Deciding on a branching strategy for a new project or team
- Creating a release or version tag
- Setting up commit message linting or changelog generation
Branching Strategies
Comparison Table
| Strategy | Branches Used | Release Cadence | Team Size Fit | Pros | Cons |
|---|---|---|---|---|---|
| GitHub Flow | main + feature branches |
Continuous (deploy on merge) | Small–medium | Simple, fast feedback, CD-friendly | No built-in release staging |
| Git Flow | main, develop, feature/*, release/*, hotfix/* |
Scheduled / versioned | Medium–large | Clear release lifecycle, hotfix path | Complex, slow merging, overhead |
| Trunk-Based Development | main (+ very short-lived branches) |
Continuous | Any (with CI maturity) | Maximum integration speed, minimal merge conflicts | Requires feature flags, strong CI discipline |
GitHub Flow
Developers branch from main, open a pull request, and merge back to main on approval. Merging to main triggers deployment. Suitable when every merged commit should ship.
git checkout -b feat/PROJ-42-add-oauth main
# ... commit work ...
git push -u origin feat/PROJ-42-add-oauth
# Open PR → review → merge → auto-deploy
Git Flow
Use when releases are batched on a schedule (e.g., sprint releases, versioned libraries).
# New feature
git checkout -b feature/PROJ-99-dark-mode develop
# Prepare a release
git checkout -b release/1.4.0 develop
# bump version, final fixes, then merge to main AND develop
git checkout main && git merge release/1.4.0
git tag -a v1.4.0 -m "Release v1.4.0"
# Emergency hotfix
git checkout -b hotfix/fix-login-crash main
# fix, then merge to main AND develop
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 · 323 lines · 36 tokens per session scan A cf351b562b08
development-workflow is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 3,087 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…