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/agents-mdgit clone --depth 1 https://github.com/redhuntlabs/wizardWhat 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 | $0.00644 | $0.00644 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
wizard 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 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard — For AI Agents
You are running with the Wizard plugin loaded. This file tells you what that means and how to behave.
What this plugin gives you
A library of skills (under skills/) that help the user build their own reusable AI workflows ("spells"), plus a seed library of ready-to-use spells (under spells/).
Both folders are loadable via your host's normal skill discovery mechanism.
Your behavioral commitments
-
Invoke the boot skill first. Load
skills/using-wizard/SKILL.mdbefore responding to the user. It teaches you the core conventions, including the 1% rule. -
The 1% rule. If there is even a 1% chance any spell in
spells/or any framework skill inskills/might apply to what the user is asking, invoke it. Do not skip skills because they "feel like overkill." That feeling is a rationalization. -
Iron Law. When using
building-a-spellto create a new spell, the try-it phase is non-skippable. No exceptions. The forbidden excuses are listed in the skill itself. -
Batch Iron Law. When the user asks for multiple spells in one session, complete one end-to-end before starting the next. No batched interviews followed by batched testing.
-
Personal-library-only writes. The meta-builder writes spells to
WIZARD_HOME(default~/.wizard/). Never modify the bundledspells/folder. -
Plain language. Most users are not developers. When you write or refine a spell, use plain language by default. Only switch to dev-jargon if the spell's
audiencefield isdev.
Where things live
skills/ # Framework skills (the meta-builder, etc.)
spells/ # Bundled seed library (read-only)
$WIZARD_HOME/ # User's personal library (default ~/.wizard/)
docs/ # Spec, philosophy, tutorials
agents/spell-tester.md # Subagent dispatched during try-it
commands/ # User-facing slash commands
Where to look first
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 · 53 lines · 644 tokens per session scan A 796cb5ef18d9
wizard AGENTS.md is an instructions file published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 644 tokens to every session, about $0.0032 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
squid AGENTS.md
Instructions for iusztinpaul/squid, covering squid: an opinionated software factory for claude code, key principles you will respect all over your work, what's in the repo, editing conventions and companion plugin: caveman (optional).
ai-assist-skills AGENTS.md
AGENTS.md instructions for jparkerweb/ai-assist-skills, covering agents.md, project overview, git commit messages, local development and install a single skill from your local working tree.
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
a-i--skills 02-skill-format.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering skill format instructions, skill.md file structure, required yaml frontmatter, optional yaml fields and naming rules.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.
ai-prompts AGENTS.md
Instructions for liatrio-labs/ai-prompts, covering ai agent instructions, context marker, local skill scripts, standard workflow and initialize.