Planning Prompts

Invoke via routing:

• "brief" / "new project" → Create BRIEF.md
• "roadmap" / "phases" → Create ROADMAP.md
• "plan phase" / "next phase" → Create phase PLAN.md
• "meta-prompt" / "research then plan" → Create prompt chain

Plans ARE prompts - PLAN.md is directly executable by Claude.

When planning a phase, you are writing the prompt that will execute it.

The quality degradation curve:

• 0-30% context: Peak quality (comprehensive, thorough, no anxiety)
• 30-50% context: Good quality (engaged, manageable pressure)
• 50-70% context: Degrading quality (efficiency mode, compression)
• 70%+ context: Poor quality (self-lobotomization, rushed work)

The 2-3 Task Rule: Each plan should contain 2-3 tasks maximum.

Examples:

• 01-01-PLAN.md - Phase 1, Plan 1 (2-3 tasks: database schema only)
• 01-02-PLAN.md - Phase 1, Plan 2 (2-3 tasks: database client setup)
• 01-03-PLAN.md - Phase 1, Plan 3 (2-3 tasks: API routes)

See: reference/plans.md (scope estimation section)

Checkpoint types:

• checkpoint:human-verify - Human confirms Claude's automated work (visual checks, UI verification)
• checkpoint:decision - Human makes implementation choice (auth provider, architecture)

Rarely needed: checkpoint:human-action - Only for actions with no CLI/API (email verification links, account approvals requiring web login with 2FA)

See: reference/plans.md (checkpoints section)

1. Auto-fix bugs - Broken behavior -> fix immediately, document in Summary
2. Auto-add missing critical - Security/correctness gaps -> add immediately, document
3. Auto-fix blockers - Can't proceed -> fix immediately, document
4. Ask about architectural - Major structural changes -> stop and ask user
5. Log enhancements - Nice-to-haves -> auto-log to ISSUES.md, continue

Milestones mark shipped versions: v1.0 -> v1.1 -> v2.0

If it sounds like corporate PM theater, delete it.

# Check for planning structure
ls -la .planning/ 2>/dev/null
ls -la .prompts/ 2>/dev/null

# Find any continue-here files
find . -name ".continue-here*.md" -type f 2>/dev/null

# Check for existing artifacts
[ -f .planning/BRIEF.md ] && echo "BRIEF: exists"
[ -f .planning/ROADMAP.md ] && echo "ROADMAP: exists"

Present findings before intake question.

If planning structure exists:

Project: [from BRIEF or directory]
Brief: [exists/missing]
Roadmap: [X phases defined]
Current: [phase status]

What would you like to do?
1. Plan next phase
2. Execute current phase
3. Create handoff (stopping for now)
4. View/update roadmap
5. Create a meta-prompt (for Claude-to-Claude pipeline)
6. Something else

If prompts structure exists:

Found .prompts/ directory with [N] prompt folders.
Latest: {most recent folder}

What would you like to do?
1. Create new prompt (Research/Plan/Do/Refine)
2. Run existing prompt
3. View prompt chain
4. Something else

If no structure found:

No planning or prompt structure found.

What would you like to do?
1. Start new project (create brief + roadmap)
2. Create a meta-prompt chain (research -> plan -> implement)
3. Jump straight to phase planning
4. Get guidance on approach

Wait for response before proceeding.

After reading the reference, follow it exactly.

BRIEF.md          -> Human vision (you read this)
    |
ROADMAP.md        -> Phase structure (overview)
    |
RESEARCH.md       -> Research prompt (optional, for unknowns)
    |
FINDINGS.md       -> Research output (if research done)
    |
PLAN.md           -> THE PROMPT (Claude executes this)
    |
SUMMARY.md        -> Outcome (existence = phase complete)

Structure:

.planning/
├── BRIEF.md                    # Human vision
├── ROADMAP.md                  # Phase structure + tracking
└── phases/
    ├── 01-foundation/
    │   ├── 01-01-PLAN.md       # Plan 1: Database setup
    │   ├── 01-01-SUMMARY.md    # Outcome (exists = done)
    │   ├── 01-02-PLAN.md       # Plan 2: API routes
    │   └── 01-02-SUMMARY.md
    └── 02-auth/
        ├── 02-01-RESEARCH.md   # Research prompt (if needed)
        ├── 02-01-FINDINGS.md   # Research output
        └── 02-02-PLAN.md       # Implementation prompt

.prompts/
├── 001-auth-research/
│   ├── completed/
│   │   └── 001-auth-research.md    # Prompt (archived after run)
│   ├── auth-research.md            # Full output (XML for Claude)
│   └── SUMMARY.md                  # Executive summary (markdown for human)
├── 002-auth-plan/
│   ├── completed/
│   │   └── 002-auth-plan.md
│   ├── auth-plan.md
│   └── SUMMARY.md
├── 003-auth-implement/
│   ├── completed/
│   │   └── 003-auth-implement.md
│   └── SUMMARY.md                  # Do prompts create code elsewhere

Purpose types:

• Research - Gather information that planning prompt consumes
• Plan - Create approach/roadmap that implementation consumes
• Do - Execute a task, produce an artifact
• Refine - Improve an existing research or plan output

1. Research Prompt -> Gathers information, produces structured findings
2. Plan Prompt -> References research, creates phased approach
3. Do Prompt -> References plan, implements each phase

Each stage:

• Produces output for next stage to consume
• Creates SUMMARY.md for human scanning
• Archives prompt after completion
• Captures metadata (confidence, dependencies, open questions)

Chain detection: When creating prompts, scan for existing research/plan files to reference.

Layer 1 (parallel): 001-api-research, 002-db-research, 003-ui-research
Layer 2 (depends on all): 004-architecture-plan
Layer 3 (depends on 004): 005-implement

Execution: Parallel within layers, sequential between layers.

001-auth-research        -> Initial research
002-auth-research-refine -> Deeper dive on specific finding
003-auth-plan            -> Plan based on refined research

Refine prompts preserve version history and track changes.

# {Topic} {Purpose} Summary

**{Substantive one-liner describing outcome}**

## Version
{v1 or "v2 (refined from v1)"}

## Key Findings
- {Most important finding or action}
- {Second key item}
- {Third key item}

## Files Created
{Only for Do prompts}
- `path/to/file.ts` - Description

## Decisions Needed
{Specific actionable decisions, or "None"}

## Blockers
{External impediments, or "None"}

## Next Step
{Concrete forward action}

---
*Confidence: {High|Medium|Low}*
*Full output: {filename.md}*

One-liner must be substantive:

• Good: "JWT with jose library and httpOnly cookies recommended"
• Bad: "Research completed"

<metadata>
  <confidence level="{high|medium|low}">
    {Why this confidence level}
  </confidence>
  <dependencies>
    {What's needed to proceed}
  </dependencies>
  <open_questions>
    {What remains uncertain}
  </open_questions>
  <assumptions>
    {What was assumed}
  </assumptions>
</metadata>