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/pythonnpx skills add kid-sid/codex-spellbook --skill pythongit 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 | $0.00043 | $0.00678 |
| Opus 5 | $0.00022 | $0.00339 |
| Sonnet 5 | $0.00009 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
python scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get(url, timeout=30) How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python
Prefer typed, explicit Python with validation at boundaries, modern async I/O, and simple seams over framework-heavy indirection.
When to Activate
- Add or refactor Python modules
- Choose a model type for request or domain data
- Write an outbound HTTP integration
- Add async handlers or background jobs
- Configure pytest, typing, or packaging
- Replace hidden globals with explicit dependencies
- Review Python code for type and validation drift
Typing and Modeling
| Pattern | Preferred | Avoid |
|---|---|---|
| Public functions | Full parameter and return annotations | Unannotated signatures |
| Collections | list[str], dict[str, int] |
List, Dict unless compatibility requires it |
| Optional values | `str | None` |
| Need | Use |
|---|---|
| External input validation | pydantic.BaseModel |
| Internal immutable value object | @dataclass(frozen=True) |
| Loosely structured mapping shape | TypedDict |
HTTP and Async
BAD
import requests
response = requests.get(url, timeout=30)
GOOD
import httpx
async with httpx.AsyncClient(timeout=10.0) as client:
response = await client.get(url)
| Rule | Why |
|---|---|
Use async only for real I/O boundaries |
Avoid fake async complexity |
| Do not call blocking I/O inside async handlers | Prevent event loop stalls |
Batch concurrent I/O with asyncio.TaskGroup or gather where safe |
Improve latency deterministically |
Project Layout and DI
| Section | Purpose |
|---|---|
[project] |
Metadata and dependencies |
[tool.pytest.ini_options] |
Test discovery and markers |
[tool.ruff] or [tool.black] |
Lint and format configuration |
[tool.mypy] |
Type checking configuration |
| Preferred | Avoid |
|---|---|
| Pass collaborators through constructors or function parameters | Global singletons hidden inside modules |
| Build objects in a wiring layer | Import-time side effects creating clients |
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 · 101 lines · 43 tokens per session scan A 16255e718f65
python is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 678 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…