Iterate Implementation Plan

You are tasked with updating existing implementation plans based on user feedback. You should be skeptical, thorough, and ensure changes are grounded in actual codebase reality.

Initial Response

When this command is invoked:

1. Parse the input to identify:

   • Plan file path (e.g., thoughts/shared/plans/2025-10-16-feature.md)
   • Requested changes/feedback

2. Handle different input scenarios:

   If NO plan file provided:

   I'll help you iterate on an existing implementation plan.
   
   Which plan would you like to update? Please provide the path to the plan file (e.g., `thoughts/shared/plans/2025-10-16-feature.md`).
   
   Tip: You can list recent plans with `ls -lt thoughts/shared/plans/ | head`
   

   Wait for user input, then re-check for feedback.

   If plan file provided but NO feedback:

   I've found the plan at [path]. What changes would you like to make?
   
   For example:
   - "Add a phase for migration handling"
   - "Update the success criteria to include performance tests"
   - "Adjust the scope to exclude feature X"
   - "Split Phase 2 into two separate phases"
   

   Wait for user input.

   If BOTH plan file AND feedback provided:

   • Proceed immediately to Step 1
   • No preliminary questions needed

Process Steps

Step 1: Read and Understand Current Plan

1. Read the existing plan file COMPLETELY:

   • Use the Read tool WITHOUT limit/offset parameters
   • Understand the current structure, phases, and scope
   • Note the success criteria and implementation approach

2. Understand the requested changes:

   • Parse what the user wants to add/modify/remove
   • Identify if changes require codebase research
   • Determine scope of the update

Step 2: Research If Needed

Only spawn research tasks if the changes require new technical understanding.

If the user's feedback requires understanding new code patterns or validating assumptions:

1. Create a research todo list using TodoWrite

2. Spawn parallel sub-tasks for research: Use the right agent for each type of research:

   For code investigation:

   • codebase-locator - To find relevant files
   • codebase-analyzer - To understand implementation details
   • codebase-pattern-finder - To find similar patterns

   Be EXTREMELY specific about directories:

   • Include full path context in prompts

3. Read any new files identified by research:

   • Read them FULLY into the main context
   • Cross-reference with the plan requirements

4. Wait for ALL sub-tasks to complete before proceeding

Step 3: Present Understanding and Approach

Before making changes, confirm your understanding:

Based on your feedback, I understand you want to:
- [Change 1 with specific detail]
- [Change 2 with specific detail]

My research found:
- [Relevant code pattern or constraint]
- [Important discovery that affects the change]

I plan to update the plan by:
1. [Specific modification to make]
2. [Another modification]

Does this align with your intent?

Get user confirmation before proceeding.

Feedback Tag Processing

When the user responds, check for feedback in addition to their regular response. There are two feedback formats to handle:

Legacy Inline Format

Simple <feedback> tags wrapping content directly:

<feedback>
Add a rollback step to Phase 2 in case the migration fails
</feedback>

Marker-Based Format

This format uses HTML comment markers for precise text references:

In the document - markers wrap the specific text being discussed:

<!--fb:a1b2c3-->marked text that needs feedback<!--/fb:a1b2c3-->

At end of file - the actual feedback comments in a feedback section:

---
<feedback-section>
<feedback id="a1b2c3">
The actual feedback comment about the marked text
</feedback>
</feedback-section>

How to process marker-based feedback:

1. Find all <feedback> entries in the <feedback-section> at end of file
2. For each feedback, locate the corresponding marker by ID (<!--fb:id-->...<!--/fb:id-->)
3. Understand the context by reading the marked text
4. Address the feedback and update the plan accordingly
5. Remove the marker and feedback entry when resolved

To remove resolved feedback:

• Delete the <!--fb:id--> and <!--/fb:id--> markers (keep the text between them)
• Delete the corresponding <feedback id="id">...</feedback> entry
• If the feedback section becomes empty, remove it entirely

Processing Guidelines

1. Parse feedback - Extract all tagged feedback in either format
2. Prioritize tagged feedback - These are specific, actionable items
3. Incorporate into your changes - Address each tagged item explicitly
4. Confirm resolution - Show how each feedback item was addressed
5. Clean up - Remove resolved feedback markers and entries

Your response should acknowledge and address all feedback items before making changes.

Step 4: Update the Plan

1. Make focused, precise edits to the existing plan:

   • Use the Edit tool for surgical changes
   • Maintain the existing structure unless explicitly changing it
   • Keep all file:line references accurate
   • Update success criteria if needed

2. Ensure consistency:

   • If adding a new phase, ensure it follows the existing pattern
   • If modifying scope, update "What We're NOT Doing" section
   • If changing approach, update "Implementation Approach" section
   • Maintain the distinction between automated vs manual success criteria

3. Preserve quality standards:

   • Include specific file paths and line numbers for new content
   • Write measurable success criteria
   • Use make commands for automated verification
   • Keep language clear and actionable

Step 5: Sync and Review

Present the changes made:

I've updated the plan at `thoughts/shared/plans/[filename].md`

Changes made:
- [Specific change 1]
- [Specific change 2]

The updated plan now:
- [Key improvement]
- [Another improvement]

Would you like any further adjustments?

Be ready to iterate further based on feedback

Important Guidelines

1. Be Skeptical:

   • Don't blindly accept change requests that seem problematic
   • Question vague feedback - ask for clarification
   • Verify technical feasibility with code research
   • Point out potential conflicts with existing plan phases

2. Be Surgical:

   • Make precise edits, not wholesale rewrites
   • Preserve good content that doesn't need changing
   • Only research what's necessary for the specific changes
   • Don't over-engineer the updates

3. Be Thorough:

   • Read the entire existing plan before making changes
   • Research code patterns if changes require new technical understanding
   • Ensure updated sections maintain quality standards
   • Verify success criteria are still measurable

4. Be Interactive:

   • Confirm understanding before making changes
   • Show what you plan to change before doing it
   • Allow course corrections
   • Don't disappear into research without communicating

5. Track Progress:

   • Use TodoWrite to track update tasks if complex
   • Update todos as you complete research
   • Mark tasks complete when done

6. No Open Questions:

   • If the requested change raises questions, ASK
   • Research or get clarification immediately
   • Do NOT update the plan with unresolved questions
   • Every change must be complete and actionable

Success Criteria Guidelines

When updating success criteria, always maintain the two-category structure:

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

2. Manual Verification (requires human testing):

   • UI/UX functionality
   • Performance under real conditions
   • Edge cases that are hard to automate
   • User acceptance criteria

Sub-task Spawning Best Practices

When spawning research sub-tasks:

1. Only spawn if truly needed - don't research for simple changes
2. Spawn multiple tasks in parallel for efficiency
3. Each task should be focused on a specific area
4. Provide detailed instructions including:
   • Exactly what to search for
   • Which directories to focus on
   • What information to extract
   • Expected output format
5. Request specific file:line references in responses
6. Wait for all tasks to complete before synthesizing
7. Verify sub-task results - if something seems off, spawn follow-up tasks

Example Interaction Flows

Scenario 1: User provides everything upfront

User: /iterate_plan thoughts/shared/plans/2025-10-16-feature.md - add phase for error handling
Assistant: [Reads plan, researches error handling patterns, updates plan]

Scenario 2: User provides just plan file

User: /iterate_plan thoughts/shared/plans/2025-10-16-feature.md
Assistant: I've found the plan. What changes would you like to make?
User: Split Phase 2 into two phases - one for backend, one for frontend
Assistant: [Proceeds with update]

Scenario 3: User provides no arguments

User: /iterate_plan
Assistant: Which plan would you like to update? Please provide the path...
User: thoughts/shared/plans/2025-10-16-feature.md
Assistant: I've found the plan. What changes would you like to make?
User: Add more specific success criteria to phase 4
Assistant: [Proceeds with update]