Gsd New Project

---
name: gsd-new-project
description: Orchestrate project initialization with parallel research and roadmap creation
allowed-tools: Task, Read, Edit, Bash
argument-hint: '[domain]'
---


<objective>

Initialize a new project through unified flow: questioning → research (optional) → requirements → roadmap.

This is the most leveraged moment in any project. Deep questioning here means better plans, better execution, better outcomes. One command takes you from idea to ready-for-planning.

**Creates:**
- `.planning/PROJECT.md` — project context
- `.planning/config.json` — workflow preferences
- `.planning/research/` — domain research (optional)
- `.planning/REQUIREMENTS.md` — scoped requirements
- `.planning/ROADMAP.md` — phase structure
- `.planning/STATE.md` — project memory

**After this command:** Run `/gsd-plan-phase 1` to start execution.

</objective>

<execution_context>

@.claude/get-shit-done/references/questioning.md
@.claude/get-shit-done/references/ui-brand.md
@.claude/get-shit-done/templates/project.md
@.claude/get-shit-done/templates/requirements.md

</execution_context>

<process>

## Phase 1: Setup

**MANDATORY FIRST STEP — Execute these checks before ANY user interaction:**

1. **Abort if project exists:**
   ```bash
   [ -f .planning/PROJECT.md ] && echo "ERROR: Project already initialized. Use /gsd-progress" && exit 1
   ```

2. **Initialize git repo in THIS directory** (required even if inside a parent repo):
   ```bash
   if [ -d .git ] || [ -f .git ]; then
       echo "Git repo exists in current directory"
   else
       git init
       echo "Initialized new git repo"
   fi
   ```

3. **Detect existing code (brownfield detection):**
   ```bash
   CODE_FILES=$(find . -name "*.ts" -o -name "*.js" -o -name "*.py" -o -name "*.go" -o -name "*.rs" -o -name "*.swift" -o -name "*.java" 2>/dev/null | grep -v node_modules | grep -v .git | head -20)
   HAS_PACKAGE=$([ -f package.json ] || [ -f requirements.txt ] || [ -f Cargo.toml ] || [ -f go.mod ] || [ -f Package.swift ] && echo "yes")
   HAS_CODEBASE_MAP=$([ -d .planning/codebase ] && echo "yes")
   ```

   **You MUST run all bash commands above using the Bash tool before proceeding.**

## Phase 2: Brownfield Offer

**If existing code detected and .planning/codebase/ doesn't exist:**

Check the results from setup step:
- If `CODE_FILES` is non-empty OR `HAS_PACKAGE` is "yes"
- AND `HAS_CODEBASE_MAP` is NOT "yes"

Use AskUserQuestion:
- header: "Existing Code"
- question: "I detected existing code in this directory. Would you like to map the codebase first?"
- options:
  - "Map codebase first" — Run /gsd-map-codebase to understand existing architecture (Recommended)
  - "Skip mapping" — Proceed with project initialization

**If "Map codebase first":**
```
Run `/gsd-map-codebase` first, then return to `/gsd-new-project`
```
Exit command.

**If "Skip mapping":** Continue to Phase 3.

**If no existing code detected OR codebase already mapped:** Continue to Phase 3.

## Phase 3: Deep Questioning

**Display stage banner:**

```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► QUESTIONING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

**Open the conversation:**

Ask inline (freeform, NOT AskUserQuestion):

"What do you want to build?"

Wait for their response. This gives you the context needed to ask intelligent follow-up questions.

**Follow the thread:**

Based on what they said, ask follow-up questions that dig into their response. Use AskUserQuestion with options that probe what they mentioned — interpretations, clarifications, concrete examples.

Keep following threads. Each answer opens new threads to explore. Ask about:
- What excited them
- What problem sparked this
- What they mean by vague terms
- What it would actually look like
- What's already decided

Consult `questioning.md` for techniques:
- Challenge vagueness
- Make abstract concrete
- Surface assumptions
- Find edges
- Reveal motivation

**Check context (background, not out loud):**

As you go, mentally check the context checklist from `questioning.md`. If gaps remain, weave questions naturally. Don't suddenly switch to checklist mode.

**Decision gate:**

When you could write a clear PROJECT.md, use AskUserQuestion:

- header: "Ready?"
- question: "I think I understand what you're after. Ready to create PROJECT.md?"
- options:
  - "Create PROJECT.md" — Let's move forward
  - "Keep exploring" — I want to share more / ask me more

If "Keep exploring" — ask what they want to add, or identify gaps and probe naturally.

Loop until "Create PROJECT.md" selected.

## Phase 4: Write PROJECT.md

Synthesize all context into `.planning/PROJECT.md` using the template from `templates/project.md`.

**For greenfield projects:**

Initialize requirements as hypotheses:

```markdown
## Requirements

### Validated

(None yet — ship to validate)

### Active

- [ ] [Requirement 1]
- [ ] [Requirement 2]
- [ ] [Requirement 3]

### Out of Scope

- [Exclusion 1] — [why]
- [Exclusion 2] — [why]
```

All Active requirements are hypotheses until shipped and validated.

**For brownfield projects (codebase map exists):**

Infer Validated requirements from existing code:

1. Read `.planning/codebase/ARCHITECTURE.md` and `STACK.md`
2. Identify what the codebase already does
3. These become the initial Validated set

```markdown
## Requirements

### Validated

- ✓ [Existing capability 1] — existing
- ✓ [Existing capability 2] — existing
- ✓ [Existing capability 3] — existing

### Active

- [ ] [New requirement 1]
- [ ] [New requirement 2]

### Out of Scope

- [Exclusion 1] — [why]
```

**Key Decisions:**

Initialize with any decisions made during questioning:

```markdown
## Key Decisions

| Decision | Rationale | Outcome |
|----------|-----------|---------|
| [Choice from questioning] | [Why] | — Pending |
```

**Last updated footer:**

```markdown
---
*Last updated: [date] after initialization*
```

Do not compress. Capture everything gathered.

**Commit PROJECT.md:**

```bash
mkdir -p .planning
git add .planning/PROJECT.md
git commit -m "$(cat <<'EOF'
docs: initialize project

[One-liner from PROJECT.md What This Is section]
EOF
)"
```

## Phase 5: Workflow Preferences

Ask all workflow preferences in a single AskUserQuestion call (3 questions):

```
questions: [
  {
    header: "Mode",
    question: "How do you want to work?",
    multiSelect: false,
    options: [
      { label: "YOLO (Recommended)", description: "Auto-approve, just execute" },
      { label: "Interactive", description: "Confirm at each step" }
    ]
  },
  {
    header: "Depth",
    question: "How thorough should planning be?",
    multiSelect: false,
    options: [
      { label: "Quick", description: "Ship fast (3-5 phases, 1-3 plans each)" },
      { label: "Standard", description: "Balanced scope and speed (5-8 phases, 3-5 plans each)" },
      { label: "Comprehensive", description: "Thorough coverage (8-12 phases, 5-10 plans each)" }
    ]
  },
  {
    header: "Execution",
    question: "Run plans in parallel?",
    multiSelect: false,
    options: [
      { label: "Parallel (Recommended)", description: "Independent plans run simultaneously" },
      { label: "Sequential", description: "One plan at a time" }
    ]
  }
]
```

Create `.planning/config.json` with chosen mode, depth, and parallelization.

**Commit config.json:**

```bash
git add .planning/config.json
git commit -m "$(cat <<'EOF'
chore: add project config

Mode: [chosen mode]
Depth: [chosen depth]
Parallelization: [enabled/disabled]
EOF
)"
```

## Phase 5.5: Git Identity Configuration

**Goal:** Ensure git identity is configured before agents make commits.

**Check if git is already configured:**

```bash
GIT_NAME=$(git config user.name 2>/dev/null)
GIT_EMAIL=$(git config user.email 2>/dev/null)

if [ -n "$GIT_NAME" ] && [ -n "$GIT_EMAIL" ]; then
    echo "Git identity already configured:"
    echo "  Name: $GIT_NAME"
    echo "  Email: $GIT_EMAIL"
    
    # Store source in config.json
    python3 << PYTHON
import json
import os

git_name = os.environ.get('GIT_NAME', '')
git_email = os.environ.get('GIT_EMAIL', '')

with open('.planning/config.json', 'r') as f:
    config = json.load(f)

config['git'] = {
    'author': {
        'name': git_name,
        'email': git_email
    },
    'source': 'global'
}

with open('.planning/config.json', 'w') as f:
    json.dump(config, f, indent=2)
PYTHON
    
    # Continue to next phase
fi
```

**If not configured**, use AskUserQuestion:

```yaml
header: "Git Identity Configuration"
question: |
  Git user information is needed for commit attribution. Automated agents 
  (like gsd-executor) will commit using this identity.
  
  How would you like to proceed?
options:
  - id: configure-global
    label: "Configure git globally (recommended)"
    description: "I'll set it in git config for all repositories"
  - id: project-only
    label: "Store in this project only"
    description: "Keep identity in .planning/config.json for this project"
  - id: already-done
    label: "I already configured it"
    description: "Skip this step and verify configuration"
```

**If "configure-global" selected:**

```bash
echo "Please configure git globally by running:"
echo ""
echo "  git config --global user.name \"Your Name\""
echo "  git config --global user.email \"you@example.com\""
echo ""
echo "After running these commands, type 'done' to continue."

# Wait for user confirmation (via AskUserQuestion)
# Then re-check git config and store source as "global"

GIT_NAME=$(git config user.name 2>/dev/null)
GIT_EMAIL=$(git config user.email 2>/dev/null)

if [ -z "$GIT_NAME" ] || [ -z "$GIT_EMAIL" ]; then
    echo "ERROR: Git config not detected. Please try again."
    # Loop back to question
else
    # Store in config.json
    python3 << PYTHON
import json
import os

git_name = os.environ.get('GIT_NAME', '')
git_email = os.environ.get('GIT_EMAIL', '')

with open('.planning/config.json', 'r') as f:
    config = json.load(f)

config['git'] = {
    'author': {
        'name': git_name,
        'email': git_email
    },
    'source': 'global'
}

with open('.planning/config.json', 'w') as f:
    json.dump(config, f, indent=2)
PYTHON
fi
```

**If "project-only" selected:**

```yaml
# Ask for name
header: "Git Author Name"
question: "Enter your full name for git commits:"
input_type: freeform

# Ask for email
header: "Git Author Email"
question: "Enter your email for git commits:"
input_type: freeform

# Validate and store
```

```bash
# After receiving inputs (USER_NAME, USER_EMAIL)
# Validate email contains @
if [[ ! "$USER_EMAIL" =~ "@" ]]; then
    echo "ERROR: Invalid email format (must contain @)"
    # Loop back
fi

# Store in config.json
python3 << PYTHON
import json
import os

user_name = os.environ.get('USER_NAME', '')
user_email = os.environ.get('USER_EMAIL', '')

with open('.planning/config.json', 'r') as f:
    config = json.load(f)

config['git'] = {
    'author': {
        'name': user_name,
        'email': user_email
    },
    'source': 'config'
}

with open('.planning/config.json', 'w') as f:
    json.dump(config, f, indent=2)
PYTHON

echo "Git identity stored in .planning/config.json"
```

**If "already-done" selected:**

```bash
# Verify git config returns values
GIT_NAME=$(git config user.name 2>/dev/null)
GIT_EMAIL=$(git config user.email 2>/dev/null)

if [ -z "$GIT_NAME" ] || [ -z "$GIT_EMAIL" ]; then
    echo "ERROR: Git identity not found. Please configure it first."
    # Loop back to question
else
    echo "Git identity verified."
    # Store source as "global"
    python3 << PYTHON
import json
import os

git_name = os.environ.get('GIT_NAME', '')
git_email = os.environ.get('GIT_EMAIL', '')

with open('.planning/config.json', 'r') as f:
    config = json.load(f)

config['git'] = {
    'author': {
        'name': git_name,
        'email': git_email
    },
    'source': 'global'
}

with open('.planning/config.json', 'w') as f:
    json.dump(config, f, indent=2)
PYTHON
fi
```

**Success criteria for Phase 5.5:**
- [ ] Git identity exists in git config OR .planning/config.json
- [ ] Identity includes valid name (non-empty) and email (contains @)
- [ ] Source recorded in config.json ("global", "config", or "local")

## Phase 6: Research Decision

Use AskUserQuestion:
- header: "Research"
- question: "Research the domain ecosystem before defining requirements?"
- options:
  - "Research first (Recommended)" — Discover standard stacks, expected features, architecture patterns
  - "Skip research" — I know this domain well, go straight to requirements

**If "Research first":**

Display stage banner:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► RESEARCHING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Researching [domain] ecosystem...
```

Create research directory:
```bash
mkdir -p .planning/research
```

**Determine milestone context:**

Check if this is greenfield or subsequent milestone:
- If no "Validated" requirements in PROJECT.md → Greenfield (building from scratch)
- If "Validated" requirements exist → Subsequent milestone (adding to existing app)

Display spawning indicator:
```
◆ Spawning 4 researchers in parallel...
  → Stack research
  → Features research
  → Architecture research
  → Pitfalls research
```

Spawn 4 parallel gsd-project-researcher agents with rich context:

```
Task(prompt="
<research_type>
Project Research — Stack dimension for [domain].
</research_type>

<milestone_context>
[greenfield OR subsequent]

Greenfield: Research the standard stack for building [domain] from scratch.
Subsequent: Research what's needed to add [target features] to an existing [domain] app. Don't re-research the existing system.
</milestone_context>

<question>
What's the standard 2025 stack for [domain]?
</question>

<project_context>
[PROJECT.md summary - core value, constraints, what they're building]
</project_context>

<downstream_consumer>
Your STACK.md feeds into roadmap creation. Be prescriptive:
- Specific libraries with versions
- Clear rationale for each choice
- What NOT to use and why
</downstream_consumer>

<quality_gate>
- [ ] Versions are current (verify with Context7/official docs, not training data)
- [ ] Rationale explains WHY, not just WHAT
- [ ] Confidence levels assigned to each recommendation
</quality_gate>

<output>
Write to: .planning/research/STACK.md
Use template: .claude/get-shit-done/templates/research-project/STACK.md
</output>
", subagent_type="gsd-project-researcher", description="Stack research")

Task(prompt="
<research_type>
Project Research — Features dimension for [domain].
</research_type>

<milestone_context>
[greenfield OR subsequent]

Greenfield: What features do [domain] products have? What's table stakes vs differentiating?
Subsequent: How do [target features] typically work? What's expected behavior?
</milestone_context>

<question>
What features do [domain] products have? What's table stakes vs differentiating?
</question>

<project_context>
[PROJECT.md summary]
</project_context>

<downstream_consumer>
Your FEATURES.md feeds into requirements definition. Categorize clearly:
- Table stakes (must have or users leave)
- Differentiators (competitive advantage)
- Anti-features (things to deliberately NOT build)
</downstream_consumer>

<quality_gate>
- [ ] Categories are clear (table stakes vs differentiators vs anti-features)
- [ ] Complexity noted for each feature
- [ ] Dependencies between features identified
</quality_gate>

<output>
Write to: .planning/research/FEATURES.md
Use template: .claude/get-shit-done/templates/research-project/FEATURES.md
</output>
", subagent_type="gsd-project-researcher", description="Features research")

Task(prompt="
<research_type>
Project Research — Architecture dimension for [domain].
</research_type>

<milestone_context>
[greenfield OR subsequent]

Greenfield: How are [domain] systems typically structured? What are major components?
Subsequent: How do [target features] integrate with existing [domain] architecture?
</milestone_context>

<question>
How are [domain] systems typically structured? What are major components?
</question>

<project_context>
[PROJECT.md summary]
</project_context>

<downstream_consumer>
Your ARCHITECTURE.md informs phase structure in roadmap. Include:
- Component boundaries (what talks to what)
- Data flow (how information moves)
- Suggested build order (dependencies between components)
</downstream_consumer>

<quality_gate>
- [ ] Components clearly defined with boundaries
- [ ] Data flow direction explicit
- [ ] Build order implications noted
</quality_gate>

<output>
Write to: .planning/research/ARCHITECTURE.md
Use template: .claude/get-shit-done/templates/research-project/ARCHITECTURE.md
</output>
", subagent_type="gsd-project-researcher", description="Architecture research")

Task(prompt="
<research_type>
Project Research — Pitfalls dimension for [domain].
</research_type>

<milestone_context>
[greenfield OR subsequent]

Greenfield: What do [domain] projects commonly get wrong? Critical mistakes?
Subsequent: What are common mistakes when adding [target features] to [domain]?
</milestone_context>

<question>
What do [domain] projects commonly get wrong? Critical mistakes?
</question>

<project_context>
[PROJECT.md summary]
</project_context>

<downstream_consumer>
Your PITFALLS.md prevents mistakes in roadmap/planning. For each pitfall:
- Warning signs (how to detect early)
- Prevention strategy (how to avoid)
- Which phase should address it
</downstream_consumer>

<quality_gate>
- [ ] Pitfalls are specific to this domain (not generic advice)
- [ ] Prevention strategies are actionable
- [ ] Phase mapping included where relevant
</quality_gate>

<output>
Write to: .planning/research/PITFALLS.md
Use template: .claude/get-shit-done/templates/research-project/PITFALLS.md
</output>
", subagent_type="gsd-project-researcher", description="Pitfalls research")
```

After all 4 agents complete, spawn synthesizer to create SUMMARY.md:

```
Task(prompt="
<task>
Synthesize research outputs into SUMMARY.md.
</task>

<research_files>
Read these files:
- .planning/research/STACK.md
- .planning/research/FEATURES.md
- .planning/research/ARCHITECTURE.md
- .planning/research/PITFALLS.md
</research_files>

<output>
Write to: .planning/research/SUMMARY.md
Use template: .claude/get-shit-done/templates/research-project/SUMMARY.md
Commit after writing.
</output>
", subagent_type="gsd-research-synthesizer", description="Synthesize research")
```

Display research complete banner and key findings:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► RESEARCH COMPLETE ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

## Key Findings

**Stack:** [from SUMMARY.md]
**Table Stakes:** [from SUMMARY.md]
**Watch Out For:** [from SUMMARY.md]

Files: `.planning/research/`
```

**If "Skip research":** Continue to Phase 7.

## Phase 7: Define Requirements

Display stage banner:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► DEFINING REQUIREMENTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

**Load context:**

Read PROJECT.md and extract:
- Core value (the ONE thing that must work)
- Stated constraints (budget, timeline, tech limitations)
- Any explicit scope boundaries

**If research exists:** Read research/FEATURES.md and extract feature categories.

**Present features by category:**

```
Here are the features for [domain]:

## Authentication
**Table stakes:**
- Sign up with email/password
- Email verification
- Password reset
- Session management

**Differentiators:**
- Magic link login
- OAuth (Google, GitHub)
- 2FA

**Research notes:** [any relevant notes]

---

## [Next Category]
...
```

**If no research:** Gather requirements through conversation instead.

Ask: "What are the main things users need to be able to do?"

For each capability mentioned:
- Ask clarifying questions to make it specific
- Probe for related capabilities
- Group into categories

**Scope each category:**

For each category, use AskUserQuestion:

- header: "[Category name]"
- question: "Which [category] features are in v1?"
- multiSelect: true
- options:
  - "[Feature 1]" — [brief description]
  - "[Feature 2]" — [brief description]
  - "[Feature 3]" — [brief description]
  - "None for v1" — Defer entire category

Track responses:
- Selected features → v1 requirements
- Unselected table stakes → v2 (users expect these)
- Unselected differentiators → out of scope

**Identify gaps:**

Use AskUserQuestion:
- header: "Additions"
- question: "Any requirements research missed? (Features specific to your vision)"
- options:
  - "No, research covered it" — Proceed
  - "Yes, let me add some" — Capture additions

**Validate core value:**

Cross-check requirements against Core Value from PROJECT.md. If gaps detected, surface them.

**Generate REQUIREMENTS.md:**

Create `.planning/REQUIREMENTS.md` with:
- v1 Requirements grouped by category (checkboxes, REQ-IDs)
- v2 Requirements (deferred)
- Out of Scope (explicit exclusions with reasoning)
- Traceability section (empty, filled by roadmap)

**REQ-ID format:** `[CATEGORY]-[NUMBER]` (AUTH-01, CONTENT-02)

**Requirement quality criteria:**

Good requirements are:
- **Specific and testable:** "User can reset password via email link" (not "Handle password reset")
- **User-centric:** "User can X" (not "System does Y")
- **Atomic:** One capability per requirement (not "User can login and manage profile")
- **Independent:** Minimal dependencies on other requirements

Reject vague requirements. Push for specificity:
- "Handle authentication" → "User can log in with email/password and stay logged in across sessions"
- "Support sharing" → "User can share post via link that opens in recipient's browser"

**Present full requirements list:**

Show every requirement (not counts) for user confirmation:

```
## v1 Requirements

### Authentication
- [ ] **AUTH-01**: User can create account with email/password
- [ ] **AUTH-02**: User can log in and stay logged in across sessions
- [ ] **AUTH-03**: User can log out from any page

### Content
- [ ] **CONT-01**: User can create posts with text
- [ ] **CONT-02**: User can edit their own posts

[... full list ...]

---

Does this capture what you're building? (yes / adjust)
```

If "adjust": Return to scoping.

**Commit requirements:**

```bash
git add .planning/REQUIREMENTS.md
git commit -m "$(cat <<'EOF'
docs: define v1 requirements

[X] requirements across [N] categories
[Y] requirements deferred to v2
EOF
)"
```

## Phase 8: Create Roadmap

Display stage banner:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► CREATING ROADMAP
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

◆ Spawning roadmapper...
```

Spawn gsd-roadmapper agent with context:

```
Task(prompt="
<planning_context>

**Project:**
@.planning/PROJECT.md

**Requirements:**
@.planning/REQUIREMENTS.md

**Research (if exists):**
@.planning/research/SUMMARY.md

**Config:**
@.planning/config.json

</planning_context>

<instructions>
Create roadmap:
1. Derive phases from requirements (don't impose structure)
2. Map every v1 requirement to exactly one phase
3. Derive 2-5 success criteria per phase (observable user behaviors)
4. Validate 100% coverage
5. Write files immediately (ROADMAP.md, STATE.md, update REQUIREMENTS.md traceability)
6. Return ROADMAP CREATED with summary

Write files first, then return. This ensures artifacts persist even if context is lost.
</instructions>
", subagent_type="gsd-roadmapper", description="Create roadmap")
```

**Handle roadmapper return:**

**If `## ROADMAP BLOCKED`:**
- Present blocker information
- Work with user to resolve
- Re-spawn when resolved

**If `## ROADMAP CREATED`:**

Read the created ROADMAP.md and present it nicely inline:

```
---

## Proposed Roadmap

**[N] phases** | **[X] requirements mapped** | All v1 requirements covered ✓

| # | Phase | Goal | Requirements | Success Criteria |
|---|-------|------|--------------|------------------|
| 1 | [Name] | [Goal] | [REQ-IDs] | [count] |
| 2 | [Name] | [Goal] | [REQ-IDs] | [count] |
| 3 | [Name] | [Goal] | [REQ-IDs] | [count] |
...

### Phase Details

**Phase 1: [Name]**
Goal: [goal]
Requirements: [REQ-IDs]
Success criteria:
1. [criterion]
2. [criterion]
3. [criterion]

**Phase 2: [Name]**
Goal: [goal]
Requirements: [REQ-IDs]
Success criteria:
1. [criterion]
2. [criterion]

[... continue for all phases ...]

---
```

**CRITICAL: Ask for approval before committing:**

Use AskUserQuestion:
- header: "Roadmap"
- question: "Does this roadmap structure work for you?"
- options:
  - "Approve" — Commit and continue
  - "Adjust phases" — Tell me what to change
  - "Review full file" — Show raw ROADMAP.md

**If "Approve":** Continue to commit.

**If "Adjust phases":**
- Get user's adjustment notes
- Re-spawn roadmapper with revision context:
  ```
  Task(prompt="
  <revision>
  User feedback on roadmap:
  [user's notes]

  Current ROADMAP.md: @.planning/ROADMAP.md

  Update the roadmap based on feedback. Edit files in place.
  Return ROADMAP REVISED with changes made.
  </revision>
  ", subagent_type="gsd-roadmapper", description="Revise roadmap")
  ```
- Present revised roadmap
- Loop until user approves

**If "Review full file":** Display raw `cat .planning/ROADMAP.md`, then re-ask.

**Commit roadmap (after approval):**

```bash
git add .planning/ROADMAP.md .planning/STATE.md .planning/REQUIREMENTS.md
git commit -m "$(cat <<'EOF'
docs: create roadmap ([N] phases)

Phases:
1. [phase-name]: [requirements covered]
2. [phase-name]: [requirements covered]
...

All v1 requirements mapped to phases.
EOF
)"
```

## Phase 10: Done

Present completion with next steps:

```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► PROJECT INITIALIZED ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

**[Project Name]**

| Artifact       | Location                    |
|----------------|-----------------------------|
| Project        | `.planning/PROJECT.md`      |
| Config         | `.planning/config.json`     |
| Research       | `.planning/research/`       |
| Requirements   | `.planning/REQUIREMENTS.md` |
| Roadmap        | `.planning/ROADMAP.md`      |

**[N] phases** | **[X] requirements** | Ready to build ✓

───────────────────────────────────────────────────────────────

## ▶ Next Up

**Phase 1: [Phase Name]** — [Goal from ROADMAP.md]

`/gsd-discuss-phase 1` — gather context and clarify approach

<sub>`/clear` first → fresh context window</sub>

---

**Also available:**
- `/gsd-plan-phase 1` — skip discussion, plan directly

───────────────────────────────────────────────────────────────
```

</process>

<output>

- `.planning/PROJECT.md`
- `.planning/config.json`
- `.planning/research/` (if research selected)
  - `STACK.md`
  - `FEATURES.md`
  - `ARCHITECTURE.md`
  - `PITFALLS.md`
  - `SUMMARY.md`
- `.planning/REQUIREMENTS.md`
- `.planning/ROADMAP.md`
- `.planning/STATE.md`

</output>

<success_criteria>

- [ ] .planning/ directory created
- [ ] Git repo initialized
- [ ] Brownfield detection completed
- [ ] Deep questioning completed (threads followed, not rushed)
- [ ] PROJECT.md captures full context → **committed**
- [ ] config.json has workflow mode, depth, parallelization → **committed**
- [ ] Research completed (if selected) — 4 parallel agents spawned → **committed**
- [ ] Requirements gathered (from research or conversation)
- [ ] User scoped each category (v1/v2/out of scope)
- [ ] REQUIREMENTS.md created with REQ-IDs → **committed**
- [ ] gsd-roadmapper spawned with context
- [ ] Roadmap files written immediately (not draft)
- [ ] User feedback incorporated (if any)
- [ ] ROADMAP.md created with phases, requirement mappings, success criteria
- [ ] STATE.md initialized
- [ ] REQUIREMENTS.md traceability updated
- [ ] User knows next step is `/gsd-discuss-phase 1`

**Atomic commits:** Each phase commits its artifacts immediately. If context is lost, artifacts persist.

</success_criteria>