Simple command to add AB method workflow to Claude Code
Toggle any file to view its contents.
Install AB Method in your project with a single command:
npx ab-method
This will automatically set up the AB Method in your .claude directory.
Toggle any file to view its contents.
# AB Method  A workflow system for Claude Code and Codex. It grills a problem into a domain-grounded plan, then either drives it through test-driven missions you review one at a time, or hands it to an autonomous `/goal` loop that runs to a verifiable stop condition. ## Install ```bash npx ab-method ``` The installer detects `.claude/` and/or `.agents/` and installs slash commands and skills for Claude Code, Codex, or both (it asks if neither exists). It also adds `.ab-method/` (workflow definitions and the path index), `docs/` scaffolding, `AGENTS.md` for Codex, and optional subagents for Claude Code. ### Or as a plugin Nothing is copied into your project; the plugin updates on its own. ```bash # Claude Code /plugin marketplace add ayoubben18/ab-method /plugin install ab-method@ab-method # Codex codex plugin marketplace add ayoubben18/ab-method codex plugin add ab-method@ab-method ``` Skills are namespaced `ab-method:<name>`: run `/ab-method:ab-create-task` (Claude Code) or `$ab-method:ab-create-task` (Codex), or describe what you want. A project's own `.ab-method/structure/index.yaml` overrides the bundled one. The plugin ships no slash commands or subagents. Don't combine it with `npx ab-method` in one project, or every workflow shows up twice. ## Commands On Claude Code, run a workflow as a slash command. Codex has no shared slash commands, so use the matching skill (`$ab-create-task`) or describe your intent. | Command | Purpose | |---|---| | `/mastermind` | Entry point: routes your intent to the right workflow | | `/create-task` | Grill a problem into a task with test-driven missions | | `/resume-task` | Continue a task from its progress tracker | | `/start-task` | Run a task autonomously, one subagent and one commit per mission | | `/extend-task` | Add missions to an existing task | | `/create-task-from-handoff` | Turn a tangent parked mid-grill into a task | | `/create-goal` | Write a prompt for an autonomous `/goal` loop | | `/extend-goal` | Extend a goal from what its run built | | `/create-roadmap` | Split a bigger idea into a dependency-ordered graph of tasks | | `/start-roadmap` | Run a planned roadmap in dependency order | | `/test-mission` | Add tests to code that wasn't written test-first | | `/analyze-project` | Document domain, tech stack and patterns (`/analyze-frontend`, `/analyze-backend` for one side) | | `/update-architecture` | Refresh architecture and domain docs | | `/ab-cleanup` | Compact docs to budget and remove task leftovers; also the 3.x → 4.0 migration | | `/ab-master [name]` | List workflows, or run one by name | **Task, goal or roadmap?** A task keeps you in the loop mission by mission. A goal is one objective with a checkable stop condition, run unattended. A roadmap is several ordered tasks; it can leave open decisions and uncharted areas for later. ## How it works 1. **Always grill.** Every task and goal starts with `grill-with-docs`, which checks your terms against `UBIQUITOUS_LANGUAGE.md` and `CONTEXT.md` and records decisions as ADRs. 2. **Plan before code.** Each task gets a test plan, a placement decision per capability (reuse, extend or extract), and, for new UI, a throwaway HTML prototype with several variants to pick from. 3. **Test what matters.** `verify: test` missions run through the `tdd` skill; `verify: build` missions (styling, wiring, config) rely on typecheck, build and the existing suite. 4. **Critics on both sides.** `critique-plan` checks the plan against the domain model before coding; `review-implementation` and `sync-architecture` check the diff and the docs after. They stay silent unless there is a real problem. 5. **Measure the blast radius.** `change-map` predicts which modules a task will touch, then compares that with the real diff. 6. **Park, don't guess.** A question nobody can answer yet goes in `unresolved-questions.md` with a placeholder behind one seam (`TODO(UQ-n)`); a tangent becomes a handoff. 7. **Small docs.** Domain and architecture docs have word budgets, hold only current state, and are checked by `npx ab-method check-docs`. 8. **Parallel only when you agree.** Missions and roadmap tasks run sequentially unless you allow tagging them for parallel subagents. ## File layout ``` .ab-method/ core/ Workflow definitions rules/ Communication, code and docs rules for every workflow structure/index.yaml Paths, outputs and doc budgets (all configurable) UBIQUITOUS_LANGUAGE.md Domain glossary CONTEXT.md Bounded-context overview docs/ architecture/ tech-stack.md, frontend/ and backend/ pattern topics adr/ Decision records tasks/<task>/ progress-tracker.md, change-map.md, review.md, ... goals/<goal>/ goal.md + progress-tracker.md handoffs/ Tangents awaiting their own task ``` ## Upgrading to 4.0 Existing trackers keep working. After updating, run `/ab-cleanup` once: on its own branch it migrates `index.yaml`, splits pattern docs into topics, compacts oversized docs (listing what it drops), and, with your approval, removes leftovers from completed tasks. ## Contributing See [CONTRIBUTING.md](CONTRIBUTING.md) for developing the plugin.