bb-plan（BB 计划）

Templates: If you need the template files referenced below (spec-template.md, plan-template.md, etc.), they are available in the BB-Skills repository at templates/. If installed locally, check ~/.bb-skills/templates/ or the project's templates/ directory.

User Input

$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.

1. 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

1. 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

1. Generate and dispatch research agents: For each unknown in Technical Context: Task: "Research {unknown} for {feature context}" For each technology choice: Task: "Find best practices for {tech} in {domain}"
2. 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

1. 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.)

1. 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