ai-playbook: Instructions file for Claude Code

AGENTS.md

ai-playbook AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Wizarck/ai-playbook. It costs 4,204 tokens per session, scanned C, original, MIT.

Project instructions for working on ai-playbook, a self-hosted dispatcher and shared rules repository. A dispatcher routes agents to the right project guidance, while AGENTS.md files provide those instructions.

In plain words
What is it for?
Finding the canonical development process, understanding inherited project rules, checking the AGENTS.md format, and applying the repository's review standards.
Why use it?
They require assistants to read the project's inheritance, schema, development-flow, and review rules before editing instruction files.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: UserPromptSubmit hook event, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md.

This is Wizarck/ai-playbook's own configuration. It tells Claude Code, Codex and OpenCode how to work on ai-playbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-playbook configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Wizarck/ai-playbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Wizarck/ai-playbook/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Wizarck/ai-playbook

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

agentmods badge for ai-playbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wizarck/ai-playbook/agents-md.svg)](https://agentmods.dev/instructions/wizarck/ai-playbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wizarck/ai-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/wizarck/ai-playbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,204 This file is loaded in full into every session.
When invoked 4,204 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04204 $0.04204
Opus 5 $0.02102 $0.02102
Sonnet 5 $0.00841 $0.00841
Haiku 4.5 $0.00420 $0.00420

Measured 7d ago against content hash af1f4fea9948, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

ai-playbook AGENTS.md scanned grade C 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Irreversible action confirmations** — `rm -rf`, `git push --force`, drop database, force-merge, etc.
AGENTS.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-playbook — self-hosted dispatcher

Read by agents working ON this repo (not consumers). Consumers read own project's AGENTS.md, inheriting from playbook via .ai-playbook/specs/*.

0 Bootstrap directive

Agents editing this repo MUST:

  1. Read docs/concepts/dispatcher-chain.md — inheritance + override semantics.
  2. Read specs/agents-md-v1.schema.json — frontmatter contract before editing AGENTS.md.
  3. Read docs/rules/verdict-contract.rule.md — verdict + severity rubric before QA.
  4. Then act.

1 Project identity

ai-playbook = universal norms + tooling repo. Submoduled by every consumer project. LLM-agnostic. Dogfoods own pre-commit + schema.

2 Dispatcher index

Topic Pointer
Canonical entry point — how to make any change docs/concepts/development-flow.md
Inheritance model docs/concepts/dispatcher-chain.md
Projects registry (path resolution) docs/concepts/projects-registry.md
AGENTS.md schema specs/agents-md-v1.schema.json
Taxonomy (agent/tool/skill/hook/…) docs/concepts/taxonomy.md
Verdict + severity contract docs/rules/verdict-contract.rule.md
Merge style rules docs/concepts/merge-policy.md
Conflict resolution across parallel PRs docs/rules/conflict-resolution-policy.rule.md
Degradation modes docs/concepts/degradation-modes.md
Agentic failure catalog docs/concepts/agentic-failures.md
Model routing matrix docs/concepts/model-routing.md
Prompt caching rules docs/concepts/prompt-caching.md
Parallel review discipline docs/concepts/parallel-review.md
Memory hierarchy docs/concepts/memory-hierarchy.md
Agent contract (I/O) docs/concepts/agent-contract.md
Error message standard docs/rules/error-message-standard.rule.md
Break-glass (--force-with-reason) docs/rules/break-glass.rule.md
Env var namespace docs/concepts/env-vars.md
MCP servers schema docs/concepts/mcp-servers-schema.md
Notification policy docs/concepts/notification-policy.md
Migration guide (v0→v1) docs/concepts/migration-guide.md
Retrospective cadence docs/concepts/retrospective-cadence.md
Caveman feature (concept) docs/concepts/caveman-mode.md
Caveman toggle (runbook) docs/runbooks/caveman-toggle.md
Caveman architecture + UI contract docs/operations/caveman-architecture.md
Ponytail feature (concept) docs/concepts/ponytail-mode.md
Ponytail toggle (runbook) docs/runbooks/ponytail-toggle.md
Ponytail architecture + UI contract docs/operations/ponytail-architecture.md
Graphify feature (concept) docs/concepts/graphify.md
Graphify setup (runbook) docs/runbooks/graphify-setup.md

Read the full file on GitHub · 262 lines

Changes

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.

  1. 7d ago First seen · 262 lines · 4,204 tokens per session scan C af1f4fea9948

Subscribe to this mod's changes

ai-playbook AGENTS.md is an instructions file published in the GitHub repository Wizarck/ai-playbook (6 stars, last pushed 10d ago), licensed MIT. It adds 4,204 tokens to every session, about $0.0210 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens