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 instructions/kid-sid/codex-spellbook/agents-mdgit 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 | $0.00733 | $0.00733 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
codex-spellbook AGENTS.md 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 3d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
codex-spellbook is a curated library of Codex skills, reusable task prompts, setup scripts, and stack-specific agent templates. The primary artifact is skills/<name>/SKILL.md: a modular instruction package that engineers can copy into ~/.codex/skills/ or a project-local skills directory.
Repository Layout
Canonical directories:
skills/<skill-name>/SKILL.md- installable Codex skillstask-prompts/**/*.md- reusable one-shot promptsagents/*.agents.md- full project-levelAGENTS.mdtemplatessetup-scripts/*.sh- environment bootstrap scripts for Codex VMstemplates/*/AGENTS.md- starter copies pointing to the full agent templates
Legacy source material currently also exists under instructions/, but new work should target skills/ first.
Skill File Format
Every skill file must use this structure:
---
name: kebab-case-name
description: Dense sentence that describes what the skill does and when to use it.
---
# Title
One-sentence summary.
## When to Activate
- 6-8 verb-led trigger conditions
## Content Sections
Tables, rules, code examples, BAD/GOOD pairs.
## Checklist
- [ ] 8-15 shipping checks
Skill rules:
SKILL.mdmust use YAML frontmatter with onlynameanddescription.- The folder name must match
name. - Put activation hints in
description; the body is only read after the skill triggers. - Include at least one comparison or decision table.
- Include at least one
BAD/GOODexample pair. - End with a
## Checklistsection containing unchecked checklist items. - Keep writing terse, code-forward, and directly actionable.
Canonical examples:
skills/api-design/SKILL.mdskills/coding-standards/SKILL.md
Match their density and example quality.
Task Prompt Format
Every prompt file must include:
---
name: task-name
description: What the prompt accomplishes.
category: review | generate | refactor | audit | scaffold | document
---
Prompt rules:
- Speak directly to Codex.
- Use
$UPPERCASEplaceholders for user-supplied values. - Name the files or directories Codex should inspect before acting.
- Define expected output shape and constraints explicitly.
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.
- 3d ago First seen · 111 lines · 733 tokens per session scan A 3ea582326e84
codex-spellbook AGENTS.md is an instructions file published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 733 tokens to every session, about $0.0037 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.