---
description: Create detailed implementation plans through interactive research and iteration
---

# Implementation Plan

You are tasked with creating detailed implementation plans through an interactive, iterative process. You should be skeptical, thorough, and work collaboratively with the user to produce high-quality technical specifications.

## Initial Response

When this command is invoked:

1. **Check if parameters were provided**:
   - If a file path or ticket reference was provided as a parameter, skip the default message
   - Immediately read any provided files FULLY
   - Begin the research process

2. **If no parameters provided**, respond with:
```
I'll help you create a detailed implementation plan. Let me start by understanding what we're building.

Please provide:
1. The task/ticket description (or reference to a ticket file)
2. Any relevant context, constraints, or specific requirements
3. Links to related research or previous implementations

I'll analyze this information and work with you to create a comprehensive plan.

Tip: You can also invoke this command with a requirements file directly: `/create_plan tasks/kasper-junge/001-2025-01-15-feature-name/requirements.md`
For deeper analysis, try: `/create_plan think deeply about tasks/kasper-junge/001-2025-01-15-feature-name/requirements.md`
```

Then wait for the user's input.

## Process Steps

### Step 1: Context Gathering & Initial Analysis

1. **Read all mentioned files immediately and FULLY**:
   - Requirements files (e.g., `tasks/<username>/001-2025-01-15-feature-name/requirements.md`)
   - Research documents from the task directory
   - Related implementation plans
   - Any JSON/data files mentioned
   - **IMPORTANT**: Use the Read tool WITHOUT limit/offset parameters to read entire files
   - **CRITICAL**: DO NOT spawn sub-tasks before reading these files yourself in the main context
   - **NEVER** read files partially - if a file is mentioned, read it completely

2. **Spawn initial research tasks to gather context**:
   Before asking the user any questions, use specialized agents to research in parallel:

   - Use the **codebase-locator** agent to find all files related to the task
   - Use the **codebase-analyzer** agent to understand how the current implementation works

   These agents will:
   - Find relevant source files, configs, and tests
   - Identify the specific directories to focus on (e.g., if WUI is mentioned, they'll focus on humanlayer-wui/)
   - Trace data flow and key functions
   - Return detailed explanations with file:line references

3. **Read all files identified by research tasks**:
   - After research tasks complete, read ALL files they identified as relevant
   - Read them FULLY into the main context
   - This ensures you have complete understanding before proceeding

4. **Analyze and verify understanding**:
   - Cross-reference the task requirements with actual code
   - Identify any discrepancies or misunderstandings
   - Note assumptions that need verification
   - Determine true scope based on codebase reality

5. **Present informed understanding and focused questions**:
   ```
   Based on the requirements and my research of the codebase, I understand we need to [accurate summary].

   I've found that:
   - [Current implementation detail with file:line reference]
   - [Relevant pattern or constraint discovered]
   - [Potential complexity or edge case identified]

   Questions that my research couldn't answer:
   - [Specific technical question that requires human judgment]
   - [Business logic clarification]
   - [Design preference that affects implementation]
   ```

   Only ask questions that you genuinely cannot answer through code investigation.

### Step 2: Research & Discovery

After getting initial clarifications:

1. **If the user corrects any misunderstanding**:
   - DO NOT just accept the correction
   - Spawn new research tasks to verify the correct information
   - Read the specific files/directories they mention
   - Only proceed once you've verified the facts yourself

2. **Create a research todo list** using TodoWrite to track exploration tasks

3. **Spawn parallel sub-tasks for comprehensive research**:
   - Create multiple Task agents to research different aspects concurrently
   - Use the right agent for each type of research:

   **For deeper investigation:**
   - **codebase-locator** - To find more specific files (e.g., "find all files that handle [specific component]")
   - **codebase-analyzer** - To understand implementation details (e.g., "analyze how [system] works")
   - **codebase-pattern-finder** - To find similar features we can model after

   **For web research (if needed):**
   - **web-search-researcher** - To find external documentation, tutorials, or best practices

   Each agent knows how to:
   - Find the right files and code patterns
   - Identify conventions and patterns to follow
   - Look for integration points and dependencies
   - Return specific file:line references
   - Find tests and examples

3. **Wait for ALL sub-tasks to complete** before proceeding

4. **Present findings and design options**:
   ```
   Based on my research, here's what I found:

   **Current State:**
   - [Key discovery about existing code]
   - [Pattern or convention to follow]

   **Design Options:**
   1. [Option A] - [pros/cons]
   2. [Option B] - [pros/cons]

   **Open Questions:**
   - [Technical uncertainty]
   - [Design decision needed]

   Which approach aligns best with your vision?
   ```

### Step 3: Plan Structure Development

Once aligned on approach:

1. **Create initial plan outline**:
   ```
   Here's my proposed plan structure:

   ## Overview
   [1-2 sentence summary]

   ## Implementation Phases:
   1. [Phase name] - [what it accomplishes]
   2. [Phase name] - [what it accomplishes]
   3. [Phase name] - [what it accomplishes]

   Does this phasing make sense? Should I adjust the order or granularity?
   ```

2. **Get feedback on structure** before writing details

### Step 4: Detailed Plan Writing

After structure approval:

1. **Determine username:**
   - Run the `${CLAUDE_PLUGIN_ROOT}/scripts/spec_metadata.sh` script if not already run
   - Check the script output for "Normalized Username"
   - If present → use it
   - If not present:
     - Check for "Existing Users" in the output
     - If existing users found → prompt: "Which user are you? [user1/user2/user3]: "
     - If no existing users → prompt: "Enter your name: " then normalize it (lowercase, spaces to hyphens)
   - Store the username for creating the directory path

2. **Determine the task directory**:
   - If working on an existing task (e.g., research already exists), write to that task's directory: `tasks/<username>/NNN-YYYY-MM-DD-description/plan.md`
   - If starting a new task, create a new numbered directory:
     - Check what task numbers already exist in `tasks/<username>/`
     - Use the next sequential number (e.g., if tasks/kasper-junge/003-... exists, create tasks/kasper-junge/004-...)
     - Format: `tasks/<username>/NNN-YYYY-MM-DD-description/plan.md` where:
       - `<username>` is the normalized username (e.g., kasper-junge, jonas-peterson)
       - NNN is a zero-padded 3-digit number (001, 002, etc.) - per-user numbering
       - YYYY-MM-DD is today's date
       - description is a brief kebab-case description
   - Example: `tasks/kasper-junge/005-2025-01-15-add-authentication/plan.md`

3. **Write the plan** to the task directory
4. **Use this template structure**:

````markdown
# [Feature/Task Name] Implementation Plan

## Overview

[Brief description of what we're implementing and why]

## Current State Analysis

[What exists now, what's missing, key constraints discovered]

## Desired End State

[A Specification of the desired end state after this plan is complete, and how to verify it]

### Key Discoveries:
- [Important finding with file:line reference]
- [Pattern to follow]
- [Constraint to work within]

## What We're NOT Doing

[Explicitly list out-of-scope items to prevent scope creep]

## Implementation Approach

[High-level strategy and reasoning]

## Phase 1: [Descriptive Name]

### Overview
[What this phase accomplishes]

### Changes Required:

#### 1. [Component/File Group]
**File**: `path/to/file.ext`
**Changes**: [Summary of changes]

```[language]
// Specific code to add/modify
```

### Success Criteria:

#### Automated Verification:
- [ ] Migration applies cleanly: `[project-specific command, e.g., python manage.py migrate]`
- [ ] Unit tests pass: `[project-specific command, e.g., npm test, pytest tests/unit/]`
- [ ] Type checking passes: `[if applicable, e.g., npm run typecheck, mypy src/]`
- [ ] Linting passes: `[project-specific command, e.g., npm run lint, flake8 src/]`
- [ ] Integration tests pass: `[project-specific command, e.g., npm run test:integration]`

#### Manual Verification:
- [ ] Feature works as expected when tested via UI
- [ ] Performance is acceptable under load
- [ ] Edge case handling verified manually
- [ ] No regressions in related features

**Implementation Note**: After completing this phase and all automated verification passes, pause here for manual confirmation from the human that the manual testing was successful before proceeding to the next phase.

---

## Phase 2: [Descriptive Name]

[Similar structure with both automated and manual success criteria...]

---

## Testing Strategy

### Unit Tests:
- [What to test]
- [Key edge cases]

### Integration Tests:
- [End-to-end scenarios]

### Manual Testing Steps:
1. [Specific step to verify feature]
2. [Another verification step]
3. [Edge case to test manually]

## Performance Considerations

[Any performance implications or optimizations needed]

## Migration Notes

[If applicable, how to handle existing data/systems]

## References

- Original requirements: `tasks/<username>/NNN-YYYY-MM-DD-description/requirements.md` (if applicable)
- Related research: `tasks/<username>/NNN-YYYY-MM-DD-description/research.md` (if applicable)
- Similar implementation: `[file:line]`
````

### Step 5: Review and Iterate

1. **Present the draft plan location**:
   ```
   I've created the initial implementation plan at:
   `tasks/<username>/NNN-YYYY-MM-DD-description/plan.md`

   Please review it and let me know:
   - Are the phases properly scoped?
   - Are the success criteria specific enough?
   - Any technical details that need adjustment?
   - Missing edge cases or considerations?
   ```

2. **Iterate based on feedback** - be ready to:
   - Add missing phases
   - Adjust technical approach
   - Clarify success criteria (both automated and manual)
   - Add/remove scope items

3. **Continue refining** until the user is satisfied

## Important Guidelines

1. **Be Skeptical**:
   - Question vague requirements
   - Identify potential issues early
   - Ask "why" and "what about"
   - Don't assume - verify with code

2. **Be Interactive**:
   - Don't write the full plan in one shot
   - Get buy-in at each major step
   - Allow course corrections
   - Work collaboratively

3. **Be Thorough**:
   - Read all context files COMPLETELY before planning
   - Research actual code patterns using parallel sub-tasks
   - Include specific file paths and line numbers
   - Write measurable success criteria with clear automated vs manual distinction
   - Use the project's standard testing/verification commands in success criteria

4. **Be Practical**:
   - Focus on incremental, testable changes
   - Consider migration and rollback
   - Think about edge cases
   - Include "what we're NOT doing"

5. **Track Progress**:
   - Use TodoWrite to track planning tasks
   - Update todos as you complete research
   - Mark planning tasks complete when done

6. **No Open Questions in Final Plan**:
   - If you encounter open questions during planning, STOP
   - Research or ask for clarification immediately
   - Do NOT write the plan with unresolved questions
   - The implementation plan must be complete and actionable
   - Every decision must be made before finalizing the plan

## Success Criteria Guidelines

**Always separate success criteria into two categories:**

1. **Automated Verification** (can be run by execution agents):
   - Commands that can be run: `make test`, `npm run lint`, etc.
   - Specific files that should exist
   - Code compilation/type checking
   - Automated test suites

2. **Manual Verification** (requires human testing):
   - UI/UX functionality
   - Performance under real conditions
   - Edge cases that are hard to automate
   - User acceptance criteria

**Format example:**
```markdown
### Success Criteria:

#### Automated Verification:
- [ ] Database migration runs successfully: `python manage.py migrate`
- [ ] All unit tests pass: `pytest tests/`
- [ ] No linting errors: `flake8 src/`
- [ ] API endpoint returns 200: `curl localhost:8080/api/new-endpoint`

#### Manual Verification:
- [ ] New feature appears correctly in the UI
- [ ] Performance is acceptable with 1000+ items
- [ ] Error messages are user-friendly
- [ ] Feature works correctly on mobile devices
```

## Common Patterns

### For Database Changes:
- Start with schema/migration
- Add store methods
- Update business logic
- Expose via API
- Update clients

### For New Features:
- Research existing patterns first
- Start with data model
- Build backend logic
- Add API endpoints
- Implement UI last

### For Refactoring:
- Document current behavior
- Plan incremental changes
- Maintain backwards compatibility
- Include migration strategy

## Sub-task Spawning Best Practices

When spawning research sub-tasks:

1. **Spawn multiple tasks in parallel** for efficiency
2. **Each task should be focused** on a specific area
3. **Provide detailed instructions** including:
   - Exactly what to search for
   - Which directories to focus on
   - What information to extract
   - Expected output format
4. **Be EXTREMELY specific about directories**:
   - If the requirements mention specific subsystems, specify those directories
   - Be explicit about directory paths in your research prompts
   - Include the full path context in your prompts
5. **Specify read-only tools** to use
6. **Request specific file:line references** in responses
7. **Wait for all tasks to complete** before synthesizing
8. **Verify sub-task results**:
   - If a sub-task returns unexpected results, spawn follow-up tasks
   - Cross-check findings against the actual codebase
   - Don't accept results that seem incorrect

Example of spawning multiple tasks:
```python
# Spawn these tasks concurrently:
tasks = [
    Task("Research database schema", db_research_prompt),
    Task("Find API patterns", api_research_prompt),
    Task("Investigate UI components", ui_research_prompt),
    Task("Check test patterns", test_research_prompt)
]
```

## Example Interaction Flow

```
User: /implementation_plan
Assistant: I'll help you create a detailed implementation plan...

User: We need to add authentication to the API. See tasks/kasper-junge/003-2025-01-10-api-auth/requirements.md
Assistant: Let me read that requirements file completely first...

[Reads file fully]

Based on the requirements, I understand we need to add JWT-based authentication to the API endpoints. Before I start planning, I have some questions...

[Interactive process continues...]
```