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/redhuntlabs/wizard/claude-mdgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/redhuntlabs/wizard/claude-md)<a href="https://agentmods.dev/instructions/redhuntlabs/wizard/claude-md"><img src="https://agentmods.dev/badge/instructions/redhuntlabs/wizard/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00347 | $0.00347 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
wizard CLAUDE.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.
What it actually says
Wizard — For Claude
See AGENTS.md for the full agent guidelines. This file is the Claude Code-specific entry point.
Quick orientation
- Boot skill:
skills/using-wizard/SKILL.md(auto-loaded byhooks/session-start) - Meta-builder:
skills/building-a-spell/SKILL.md - Seed library:
spells/ - User's personal library:
$WIZARD_HOME(default~/.wizard/)
How to use skills in Claude Code
Use the Skill tool. Never use Read on skill files. The Skill tool loads the content into your context as a single coherent unit.
Skill: wizard:building-a-spell
How to dispatch the tester
Use the Task tool with subagent_type: spell-tester. The agents/spell-tester.md file defines the agent.
Slash commands
All commands are thin wrappers around skills:
/build-spell→building-a-spell/cast-spell [name]→ loads and runs the named spell/list-spells→discovering-spells/refine-spell [name]→refining-a-spell/share-spell [name]→sharing-a-spell
The 1% rule
If you think there is even a 1% chance any skill or spell applies to what you are doing, invoke it. This is non-negotiable. Read skills/using-wizard/SKILL.md for the full reasoning.
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 · 37 lines · 347 tokens per session scan A cf9f8ab9be06
wizard CLAUDE.md is an instructions file published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 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 2026-08-31.
Other instructions, from other repositories
skillfile CLAUDE.md
Instructions for eljulians/skillfile, covering skillfile development guide, project shape, architecture standards, fragility controls and commands.
festival AGENTS.md
Instructions for Obedience-Corp/festival, covering festival, what ships and learn more.
awesome-qa-skills AGENTS.md
AGENTS.md instructions for naodeng/awesome-qa-skills, covering agents.md, project overview, repository map (edit here), skill.md conventions and agents/openai.yaml.
festival GEMINI.md
Instructions for Obedience-Corp/festival: Festival is a goal-oriented project management methodology for human and AI development workflows, driven by the fest and camp CLIs, installed and kept in sync by a third tool, festival. The skills imported below describe how to plan and execute festivals. Load them when…
ai-assist-skills CLAUDE.md
Claude Code instructions for jparkerweb/ai-assist-skills: CRITICAL — MANDATORY FIRST STEP: You MUST read AGENTS.md before responding to ANY user message, including simple questions. Do NOT skip this step regardless of how trivial the request appears. No exceptions.
ux-ui-agent-skills CLAUDE.md
Claude Code instructions for sterlingpathological200/ux-ui-agent-skills, covering ux/ui expert agent — claude design system skill, decision framework, design principles, atomic design and design thinking.