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/claude-codenpx skills add kid-sid/codex-spellbook --skill claude-codegit 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 | $0.00038 | $0.03884 |
| Opus 5 | $0.00019 | $0.01942 |
| Sonnet 5 | $0.00008 | $0.00777 |
| Haiku 4.5 | $0.00004 | $0.00388 |
Grade D, and why
claude-code scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Settings are merged: `settings.local.json` overrides `.claude/settings.json` overrides `~/.claude/settings.json`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"command": "bash -c 'echo $CLAUDE_TOOL_INPUT | grep -q \"rm -rf\" && { echo \"rm -rf blocked\"; exit 2; } || exit 0'" How it starts
The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Setup
Configuration and customization reference for Claude Code — skills, commands, agents, hooks, permissions, and MCP servers.
When to Activate
- Setting up skills, slash commands, or agents in a new project or globally
- Writing or debugging hook configurations in
settings.json - Configuring tool permissions to reduce approval prompts
- Registering or troubleshooting an MCP server
- Writing
CLAUDE.mdproject instructions - Asking how Claude Code loads context or resolves settings
- Integrating Claude Code with VS Code or JetBrains
Directory Layout
~/.claude/ # global — applies to all projects
├── settings.json # global permissions, hooks, env vars
├── CLAUDE.md # global instructions read at every session
├── skills/
│ └── <name>/skill.md # or <name>.md (flat)
├── agents/
│ └── <name>.md
└── commands/
└── <name>.md
<project>/
├── CLAUDE.md # project instructions (commit this)
└── .claude/
├── settings.json # project permissions + hooks (commit this)
├── settings.local.json # personal overrides (gitignore this)
├── skills/ # project-scoped skills
├── agents/ # project-scoped agents
└── commands/ # project-scoped commands
Settings are merged: settings.local.json overrides .claude/settings.json overrides ~/.claude/settings.json.
Skills
Skills are markdown files that Claude loads contextually when the task matches.
File Format
---
name: my-skill
description: One keyword-dense sentence used for activation matching.
---
# Title
One-sentence intro.
## When to Activate
- Verb-leading trigger condition
- Another trigger condition
## Content sections…
## Checklist
- [ ] At least one item
Installation
# Single skill (global)
cp -r skills/my-skill ~/.claude/skills/
# All skills from a library
cp -r skills/* ~/.claude/skills/
# Project-scoped (available only in this project)
cp -r skills/my-skill .claude/skills/
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 · 543 lines · 38 tokens per session scan D 2cc0120a7c8b
claude-code is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 3,884 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.