# Playbook > Free, open-source plugins for Claude Code and Codex CLI. Your agent records decisions in a Git wiki, builds in stages, checks its work, and turns repeated mistakes into rules. Made by NeuralMind (https://neuralmind.lat/en/). Version 3.6.0, MIT License. Playbook is a set of free plugins for Claude Code and Codex CLI. You decide what the software should do; the agent records it in your repo, builds from it, shows how it checked the result, and turns repeated mistakes into rules. ## How it works Every new feature or phase is a work with its own folder in docs/wiki/. The agent proposes, asks one question at a time, and records your answer word for word. 1. **Wiki**: What the product must do and must not do, who uses it, and every open question. 2. **Technology**: The stack, the limits, and what each choice costs, checked against current docs. 3. **Skills**: Which agent skills the work needs, and which ones exist already. 4. **Design system**: Tokens, components, and patterns, before a single screen is built. 5. **Plan**: Units of work, each with the paths it touches and how it will be accepted. 6. **Execution**: The agent builds unit by unit, records the evidence, and asks you to accept. Repeated mistakes become rules. A review agent reads every risky change from a fresh context. Each defect it finds is stored as evidence under a kind of mistake. When three reviews hit the same kind, Playbook proposes one rule, and the agents that write and review code get it every time they start. ## Plugins - [playbook](https://github.com/andresfrei/playbook/blob/main/plugins/playbook/README.md): The setup wizard, /playbook:init: choose the components and their scope. - [playbook-wiki](https://github.com/andresfrei/playbook/blob/main/plugins/playbook-wiki/README.md): Project memory: decisions kept in Git, each work prepared in six stages, checks on the wiki before commits and merges. - [playbook-agents](https://github.com/andresfrei/playbook/blob/main/plugins/playbook-agents/README.md): A working team: explore maps code, write builds, review reviews, classify stores findings as evidence. Plus working rules and skills. ## Install Copy the prompt for your client into a session. Then run /playbook:init in your project. - Claude Code prompt: ```text Install Playbook for Claude Code from https://github.com/andresfrei/playbook. Add its marketplace with `claude plugin marketplace add andresfrei/playbook` if it is missing. Run `claude plugin install playbook@playbook --scope user`. Use `claude plugin list` to confirm the plugin is enabled and tell me its version. Then tell me how to start a fresh Claude Code session in my project and run /playbook:init so I can choose the components and scope. ``` - Codex CLI prompt: ```text Install Playbook for Codex CLI from https://github.com/andresfrei/playbook. Ask me which setup I want: 1 for the wiki only, or 2 for the wiki and agents. Use my local Playbook checkout if it contains codex/install.py. Otherwise, clone the repository into a fresh directory. From the checkout root, run `python3 codex/install.py` and supply my choice when it prompts. Report what was installed and any existing profiles the installer kept. Show me which hooks to review in /hooks, then how to start a fresh Codex session in my project. ``` ## Links - Repository: https://github.com/andresfrei/playbook - Releases: https://github.com/andresfrei/playbook/releases - [English](https://playbook.neuralmind.lat/), [Spanish](https://playbook.neuralmind.lat/es/), [Portuguese](https://playbook.neuralmind.lat/pt/)