---
name: bb-plan
description: Execute the implementation planning workflow using the plan template to generate design artifacts.
argument-hint: <tech stack and context>
---

> **Templates:** If you need the template files referenced below (spec-template.md, plan-template.md, etc.), use the plugin-local `templates/` directory that ships with BuildBetter Skills for Codex. If the current repo already has its own `templates/` directory, prefer the repo copy.

## User Input

```text
$ARGUMENTS
```

You **MUST** consider the user input before proceeding (if not empty).

## Outline

1. **Setup**: Locate the current feature directory by finding the active feature branch and its corresponding specs directory. Parse for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").

2. **Load context**: Read FEATURE_SPEC and `constitution.md` (project-relative; check project root or `docs/` directory). Load IMPL_PLAN template (already copied). Also load BuildBetter artifacts when present:
   - `FEATURE_DIR/buildbetter-context.md`
   - `FEATURE_DIR/buildbetter-context.json`
   - `FEATURE_DIR/user-stories.md`
   Treat these as evidence inputs for planning decisions and tradeoff rationale.

3. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:
   - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
   - Fill Constitution Check section from constitution
   - Fill BuildBetter Context section from evidence artifacts (or explicitly state unavailable)
   - Evaluate gates (ERROR if violations unjustified)
   - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
   - Phase 1: Generate data-model.md, contracts/, quickstart.md
   - Ensure plan references product taxonomy, product areas, domains, and customers affected (if available from BuildBetter context)
   - Phase 1: Update agent context as needed
   - Re-evaluate Constitution Check post-design

4. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, generated artifacts, and whether BuildBetter evidence was used.

## Phases

### Phase 0: Outline & Research

1. **Extract unknowns from Technical Context** above:
   - For each NEEDS CLARIFICATION -> research task
   - For each dependency -> best practices task
   - For each integration -> patterns task
   - For each evidence-backed customer pain point -> validation task in research

2. **Generate and dispatch research agents**:

   ```text
   For each unknown in Technical Context:
     Task: "Research {unknown} for {feature context}"
   For each technology choice:
     Task: "Find best practices for {tech} in {domain}"
   ```

3. **Consolidate findings** in `research.md` using format:
   - Decision: [what was chosen]
   - Rationale: [why chosen]
   - Alternatives considered: [what else evaluated]
   - Evidence linkage: [BuildBetter evidence IDs and quotes that influenced the decision]

**Output**: research.md with all NEEDS CLARIFICATION resolved

### Phase 1: Design & Contracts

**Prerequisites:** `research.md` complete

1. **Extract entities from feature spec** -> `data-model.md`:
   - Entity name, fields, relationships
   - Validation rules from requirements
   - State transitions if applicable

2. **Define interface contracts** (if project has external interfaces) -> `/contracts/`:
   - Identify what interfaces the project exposes to users or other systems
   - Document the contract format appropriate for the project type
   - Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications
   - Skip if project is purely internal (build scripts, one-off tools, etc.)

3. **Agent context update**:
   - Update the appropriate agent-specific context file if needed
   - Add only new technology from current plan
   - Preserve manual additions between markers

**Output**: data-model.md, /contracts/*, quickstart.md, agent-specific file

## Key rules

- Use absolute paths
- ERROR on gate failures or unresolved clarifications