Skip to content
Playbook

v3.6.0Open source · MIT

Your coding agent, with a method.

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.

★ Star on GitHub

Works with Claude Code and Codex CLI

docs/wiki/works/playbook-product/decisions.md

ID
playbook-product-26
Decision
English at /, Spanish at /es/, Portuguese at /pt/, with automatic detection.
Who decided
owner
Their words
"si, ingles raiz, pero que detecte automaticamente"
Kind
definition
A real decision, as Playbook records it

01The problem

Agents forget. Your repository should not.

  • Decisions vanish in the chat

    What you agreed with the agent lives in a session that ends. Next week nobody knows why the code is the way it is.

  • Every session starts from zero

    A teammate, or the agent itself tomorrow, cannot see what was decided, what changed, or which question is still open.

  • The same mistakes come back

    Reviews catch the same kind of bug again and again, because nothing turns a lesson into a rule the agent follows.

02How it works

Six stages before any code. You close each one.

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. 01

    Wiki

    What the product must do and must not do, who uses it, and every open question.

  2. 02

    Technology

    The stack, the limits, and what each choice costs, checked against current docs.

  3. 03

    Skills

    Which agent skills the work needs, and which ones exist already.

  4. 04

    Design system

    Tokens, components, and patterns, before a single screen is built.

  5. 05

    Plan

    Units of work, each with the paths it touches and how it will be accepted.

  6. 06

    Execution

    The agent builds unit by unit, records the evidence, and asks you to accept.

03It learns

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.

  1. 01review finds a defect
  2. 02classify stores it as evidence
  3. 03three hits on one kind
  4. 04a rule every agent follows

04Plugins

Three plugins. Take the wiki alone, or add the team.

  • playbook

    The setup wizard, /playbook:init: choose the components and their scope.

    Read the guide →
  • playbook-wiki

    Project memory: decisions kept in Git, each work prepared in six stages, checks on the wiki before commits and merges.

    Read the guide →
  • playbook-agents

    A working team: explore maps code, write builds, review reviews, classify stores findings as evidence. Plus working rules and skills.

    Read the guide →

05Install

Paste one prompt. Your agent does the rest.

Copy the prompt for your client into a session. Then run /playbook:init in your project.

Claude Code

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

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.

06News

It grows by building itself.

Every release since the first, read from the repository. Each review finding Playbook records can become a rule it ships in the next version.

Releases and rules learned, cumulative
  • releases
  • rules learned
Releases and rules learned, cumulative: 19 releases, 13 rules learned (Nov 20, 2026).05101520Nov 14Nov 16Nov 18Nov 20

19 releases13 rules learned

See the data as a table
VersionDatereleasesrules learned
1.0.0Nov 14, 202610
2.0.0Nov 17, 202620
2.1.0Nov 17, 202630
2.2.0Nov 17, 202640
2.2.1Nov 17, 202650
2.2.2Nov 17, 202660
2.3.0Nov 18, 202670
2.4.0Nov 18, 202680
2.5.0Nov 19, 202690
2.6.0Nov 19, 2026100
3.0.0Nov 19, 2026110
3.1.0Nov 19, 2026120
3.1.1Nov 19, 2026130
3.2.0Nov 19, 2026140
3.2.1Nov 19, 2026150
3.3.0Nov 20, 2026160
3.4.0Nov 20, 2026174
3.5.0Nov 20, 2026189
3.6.0Nov 20, 20261913

Release notes in English, as published on GitHub.

  1. v3.6.0Nov 20, 2026

    Dedicated agents for repeated tasks

    At the close of each work, Playbook now records the tasks the agent carried out, and proposes a dedicated agent, on a model that fits the task, for a task that repeats (work task-agents, #44).

    Release notes →
  2. v3.5.0Nov 20, 2026

    Units built in parallel

    A work's plan now says which units can be built at the same time, and stage 6 builds them in parallel (work parallel-units, #42).

    Release notes →
  3. v3.4.0Nov 20, 2026

    Ask before what cannot be undone

    Claude Code now asks you before the actions you cannot take back, and a new command protects a repository's secrets (work ask-before-irreversible, #40).

    Release notes →
See all 19 releases ↓
  1. v3.3.0Nov 20, 2026

    Evidence seeded from past reviews

    A repository can now start its evidence page from the reviews it already had (work seed-evidence, #38).

    Release notes →
  2. v3.2.1Nov 19, 2026

    playbook-agents: when a review ends with findings and starts no classify, the hook now stops it once per subagent.

    Before, stop_hook_active was not set on the repeated stops of one review, so a review that could not start the classifier was stopped again and again (repeated-corrections-31, #36).

    Release notes →
  3. v3.2.0Nov 19, 2026

    Learned rules from repeated review findings

    When review keeps finding the same kind of mistake, the agent now learns from it (work repeated-corrections, #34).

    Release notes →
  4. v3.1.1Nov 19, 2026

    A fix to the version notice of 3.1.0.

    Release notes →
  5. v3.1.0Nov 19, 2026

    Claude Code does not tell you when a plugin from this marketplace has a new version.

    From 3.1.0, the playbook tells you itself, at the start of a session, and the notice about your wiki's format now reaches you, not only the agent.

    Release notes →
  6. v3.0.0Nov 19, 2026

    Version 3 lets you delegate a kind of question, so the agent stops asking the ones you always answer "yes" to.

    It is a major version: it moves a project's wiki to format 5.

    Release notes →
  7. v2.6.0Nov 19, 2026

    prepare-project now asks how a work is delivered, before any code.

    Release notes →
  8. v2.5.0Nov 19, 2026

    Three commands to start and configure Playbook in Claude Code.

    Release notes →
  9. v2.4.0Nov 18, 2026

    Playbook now supports Codex CLI alongside Claude Code.

    Release notes →
  10. v2.3.0Nov 18, 2026

    Version 2.3.0 makes the agent review read a risky change before it is committed, instead of relying on the agent to remember rule R20.

    It adds two hooks to playbook-agents and breaks nothing.

    Release notes →
  11. v2.2.2Nov 17, 2026

    Version 2.2.2 makes the report of review-change and the questions of prepare-project closer to what each skill says, and makes their evaluation cases read the meaning of an answer.

    It breaks nothing.

    Release notes →
  12. v2.2.1Nov 17, 2026

    Version 2.2.1 fixes skills that did not load when a request called for them, and a script that failed in a sandbox.

    It breaks nothing.

    Release notes →
  13. v2.2.0Nov 17, 2026

    Version 2.2.0 brings the skills in line with the best practices for skills that Anthropic and agentskills.io publish, and breaks nothing.

    Release notes →
  14. v2.1.0Nov 17, 2026

    Version 2.1.0 adds two things to playbook-wiki and breaks nothing.

    Release notes →
  15. v2.0.0Nov 17, 2026

    Version 2 splits the playbook into a shared core, for everyone who works on a project, and the owner's agent system, which anyone may use.

    It is a major version: it breaks an installation of version 1.

    Release notes →
  16. v1.0.0Nov 14, 2026

    First public release of the playbook: one person's working rules, skills, and agents for AI coding agents, shared as it is.

    Release notes →

07Open source

Free, MIT, and built with itself.

Playbook is developed with Playbook: its own repository holds the decisions, the plans, and the evidence that shaped every release. Read them, fork it, open an issue.

Current version
v3.6.0
License
MIT

08Coming soon

A store of agents and skills.

Playbook already turns repeated mistakes into rules and creates dedicated agents for tasks that repeat. Next: a place to share them. It is not open yet.

  1. 01

    Back up

    Keep your global agents and skills safe, not only on your machine.

  2. 02

    Publish

    Share an agent or a skill that works, so others can install it.

  3. 03

    Install

    Browse what others shared and add it to your setup.

Tell me when it opens

By sending, you agree that we use your data to answer you. Privacy policy