一键导入
iterate-plan
Iterate on existing implementation plans with thorough research and updates
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Iterate on existing implementation plans with thorough research and updates
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Review PR comments rigorously, present a justified summary, then post agreed responses individually
Create git commits with user approval, semantic commit format, and no Claude attribution
Implement technical plans from thoughts/shared/plans with verification
Create detailed implementation plans through interactive research and iteration
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Analyze and improve test code quality using Kent Beck's Test Desiderata framework. Use when analyzing test files, reviewing test code, identifying test quality issues, suggesting test improvements, or when asked to evaluate tests against best practices. Applies to unit tests, integration tests, and any automated test code.
| name | iterate-plan |
| description | Iterate on existing implementation plans with thorough research and updates |
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.
When this command is invoked:
Input: $ARGUMENTS
Parse $ARGUMENTS to identify:
thoughts/shared/plans/2025-10-16-feature.md)Handle different input scenarios:
If $ARGUMENTS is empty (no plan file or feedback):
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 and changes to make.
Usage: /stepwise-core:iterate-plan [plan-file-path] [changes to make]
Example: /stepwise-core:iterate-plan thoughts/shared/plans/2025-10-16-feature.md add error handling phase
Tip: You can list recent plans with `ls -lt thoughts/shared/plans/ | head`
Wait for user input, then re-check for feedback.
If $ARGUMENTS contains only plan file path (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 $ARGUMENTS contains BOTH plan file AND feedback:
Read the existing plan file COMPLETELY:
Understand the requested changes:
Only spawn research tasks if the changes require new technical understanding.
If the user's feedback requires understanding new code patterns or validating assumptions:
Create a research todo list using TodoWrite
Spawn parallel sub-tasks for research: Use the right agent for each type of research:
For code investigation:
For historical context:
Be EXTREMELY specific about directories:
frontend/ or web/ directorybackend/ or api/ directoryRead any new files identified by research:
Wait for ALL sub-tasks to complete before proceeding
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.
Ensure thoughts directory is initialized:
thoughts/ directory existsbash ${CLAUDE_PLUGIN_ROOT}/skills/thoughts-management/scripts/thoughts-init
Make focused, precise edits to the existing plan:
Ensure consistency:
Preserve quality standards:
make commands for automated verificationSync the updated plan:
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
When iteration is complete, inform the user:
Plan updated: `thoughts/shared/plans/[filename].md`
Next steps in the workflow:
- Review the updated plan
- Use `/stepwise-core:implement-plan thoughts/shared/plans/[filename].md` to execute it
- Or use `/stepwise-core:iterate-plan thoughts/shared/plans/[filename].md [more changes]` for further refinement
Tip: Use `/clear` to free up context before starting implementation
Be Skeptical:
Be Surgical:
Be Thorough:
Be Interactive:
Track Progress:
No Open Questions:
When updating success criteria, always maintain the two-category structure:
Automated Verification (can be run by execution agents):
make test, npm run lint, etc.make commands: make -C frontend check instead of cd frontend && npm run fmtManual Verification (requires human testing):
When spawning research sub-tasks:
Scenario 1: User provides everything upfront
User: /stepwise-core: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: /stepwise-core: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: /stepwise-core: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
Assistant: [Proceeds with update]