speckit.plan

## User Input

```text
$ARGUMENTS
```

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

## Outline

1. **Setup**: Run `.specify/scripts/bash/setup-plan.sh --json` from repo root and parse JSON 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 `.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied).

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
   - Evaluate gates (ERROR if violations unjustified)
   - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
   - Phase 1: Generate data-model.md, contracts/, quickstart.md
   - Phase 1: Update agent context by running the agent script
   - Re-evaluate Constitution Check post-design

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

## 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

2. **Library-First Search** (MANDATORY before research):
   - For each major component (>20 lines expected), search for existing libraries:
     - WebSearch: "npm {functionality} library 2024" or "python {functionality} package"
     - Context7: documentation for candidate libraries
     - Check: weekly downloads >1000, commits in last 6 months, TypeScript/types support
   - Document library decisions in research.md

3. **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}"
   ```

4. **Research Considerations**:
   - **Simple research**: Questions solvable with available tools (Grep, Read, WebSearch, Context7) - resolve immediately
   - **Complex research**: Requires deep investigation → create research prompt in `FEATURE_DIR/research/` for deepresearch tool

5. **Consolidate findings** in `research.md` using format:
   - Decision: [what was chosen]
   - Rationale: [why chosen]
   - Alternatives considered: [what else evaluated]
   - Library: [if applicable - name, version, why chosen over alternatives]

**Output**: research.md with all NEEDS CLARIFICATION resolved, research/ with complex research prompts (if any)

### 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. **Generate API contracts** from functional requirements:
   - For each user action → endpoint
   - Use standard REST/GraphQL patterns
   - Output OpenAPI/GraphQL schema to `/contracts/`

3. **Agent context update**:
   - Run `.specify/scripts/bash/update-agent-context.sh claude`
   - These scripts detect which AI agent is in use
   - Update the appropriate agent-specific context file
   - 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
- Library-first: Always check for existing libraries before planning custom implementations