@prpm-converter/cursorrules-subagent-driven-development

# Subagent Driven Development - Cursor Rules

---

## Overview

This cursor rule is based on the Claude Code "Subagent Driven Development" skill, adapted for use in Cursor IDE.

## Core Methodology

When working on code, follow this subagent driven development methodology:

1. *Dispatch fresh subagent:**
2. *Subagent reports back** with summary of work.
3. *Dispatch code-reviewer subagent:**
4. *Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment
5. *If issues found:**
6. Fix Critical issues immediately
7. Fix Important issues before next task
8. Note Minor issues
9. *Dispatch follow-up subagent if needed:**
10. Mark task as completed in TodoWrite
11. Move to next task
12. Repeat steps 2-5
13. Reviews entire implementation
14. Checks all plan requirements met
15. Validates overall architecture
16. Announce: "I'm using the finishing-a-development-branch skill to complete this work."
17. **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
18. Follow that skill to verify tests, present options, execute choice
19. *vs. Manual execution:**
20. Subagents follow TDD naturally
21. Fresh context per task (no confusion)
22. Parallel-safe (subagents don't interfere)
23. *vs. Executing Plans:**
24. Same session (no handoff)
25. Continuous progress (no waiting)
26. Review checkpoints automatic
27. *Cost:**
28. More subagent invocations
29. But catches issues early (cheaper than debugging later)
30. *Never:**
31. Skip code review between tasks
32. Proceed with unfixed Critical issues
33. Dispatch multiple implementation subagents in parallel (conflicts)
34. Implement without reading plan task
35. *If subagent fails task:**
36. Dispatch fix subagent with specific instructions
37. Don't try to fix manually (context pollution)
38. *Required workflow skills:**
39. **writing-plans** - REQUIRED: Creates the plan that this skill executes
40. **requesting-code-review** - REQUIRED: Review after each task (see Step 3)
41. **finishing-a-development-branch** - REQUIRED: Complete development after all tasks (see Step 7)
42. *Subagents must use:**
43. **test-driven-development** - Subagents follow TDD for each task
44. *Alternative workflow:**
45. **executing-plans** - Use for parallel session instead of same-session execution

## Principles

- Apply best practices from the skill content below

## Implementation Guidelines

- Reference the detailed skill content for specific guidance



## Integration with Other Rules

This rule works best when combined with:
- Code quality and style guidelines
- Testing best practices
- Project-specific conventions

You can reference other .cursorrules files by organizing them in your project:
```
.cursorrules/
  ├── base/
  │   ├── subagent-driven-development.cursorrules (this file)
  │   └── code-quality.cursorrules
  └── project-specific.cursorrules
```

## Original Skill Content

The following is the complete content from the Claude Code skill for reference:

---

---
name: subagent-driven-development
description: Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
---

# Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with code review after each.

**Core principle:** Fresh subagent per task + review between tasks = high quality, fast iteration

## Overview

**vs. Executing Plans (parallel session):**
- Same session (no context switch)
- Fresh subagent per task (no context pollution)
- Code review after each task (catch issues early)
- Faster iteration (no human-in-loop between tasks)

**When to use:**
- Staying in this session
- Tasks are mostly independent
- Want continuous progress with quality gates

**When NOT to use:**
- Need to review plan first (use executing-plans)
- Tasks are tightly coupled (manual execution better)
- Plan needs revision (brainstorm first)

## The Process

### 1. Load Plan

Read plan file, create TodoWrite with all tasks.

### 2. Execute Task with Subagent

For each task:

**Dispatch fresh subagent:**
```
Task tool (general-purpose):
  description: "Implement Task N: [task name]"
  prompt: |
    You are implementing Task N from [plan-file].

    Read that task carefully. Your job is to:
    1. Implement exactly what the task specifies
    2. Write tests (following TDD if task says to)
    3. Verify implementation works
    4. Commit your work
    5. Report back

    Work from: [directory]

    Report: What you implemented, what you tested, test results, files changed, any issues
```

**Subagent reports back** with summary of work.

### 3. Review Subagent's Work

**Dispatch code-reviewer subagent:**
```
Task tool (code-reviewer):
  Use template at requesting-code-review/code-reviewer.md

  WHAT_WAS_IMPLEMENTED: [from subagent's report]
  PLAN_OR_REQUIREMENTS: Task N from [plan-file]
  BASE_SHA: [commit before task]
  HEAD_SHA: [current commit]
  DESCRIPTION: [task summary]
```

**Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment

### 4. Apply Review Feedback

**If issues found:**
- Fix Critical issues immediately
- Fix Important issues before next task
- Note Minor issues

**Dispatch follow-up subagent if needed:**
```
"Fix issues from code review: [list issues]"
```

### 5. Mark Complete, Next Task

- Mark task as completed in TodoWrite
- Move to next task
- Repeat steps 2-5

### 6. Final Review

After all tasks complete, dispatch final code-reviewer:
- Reviews entire implementation
- Checks all plan requirements met
- Validates overall architecture

### 7. Complete Development

After final review passes:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice

## Example Workflow

```
You: I'm using Subagent-Driven Development to execute this plan.

[Load plan, create TodoWrite]

Task 1: Hook installation script

[Dispatch implementation subagent]
Subagent: Implemented install-hook with tests, 5/5 passing

[Get git SHAs, dispatch code-reviewer]
Reviewer: Strengths: Good test coverage. Issues: None. Ready.

[Mark Task 1 complete]

Task 2: Recovery modes

[Dispatch implementation subagent]
Subagent: Added verify/repair, 8/8 tests passing

[Dispatch code-reviewer]
Reviewer: Strengths: Solid. Issues (Important): Missing progress reporting

[Dispatch fix subagent]
Fix subagent: Added progress every 100 conversations

[Verify fix, mark Task 2 complete]

...

[After all tasks]
[Dispatch final code-reviewer]
Final reviewer: All requirements met, ready to merge

Done!
```

## Advantages

**vs. Manual execution:**
- Subagents follow TDD naturally
- Fresh context per task (no confusion)
- Parallel-safe (subagents don't interfere)

**vs. Executing Plans:**
- Same session (no handoff)
- Continuous progress (no waiting)
- Review checkpoints automatic

**Cost:**
- More subagent invocations
- But catches issues early (cheaper than debugging later)

## Red Flags

**Never:**
- Skip code review between tasks
- Proceed with unfixed Critical issues
- Dispatch multiple implementation subagents in parallel (conflicts)
- Implement without reading plan task

**If subagent fails task:**
- Dispatch fix subagent with specific instructions
- Don't try to fix manually (context pollution)

## Integration

**Required workflow skills:**
- **writing-plans** - REQUIRED: Creates the plan that this skill executes
- **requesting-code-review** - REQUIRED: Review after each task (see Step 3)
- **finishing-a-development-branch** - REQUIRED: Complete development after all tasks (see Step 7)

**Subagents must use:**
- **test-driven-development** - Subagents follow TDD for each task

**Alternative workflow:**
- **executing-plans** - Use for parallel session instead of same-session execution

See code-reviewer template: requesting-code-review/code-reviewer.md


---

## Usage Notes

- Apply these principles consistently throughout development
- Adapt the methodology to fit your specific project context
- Combine with project-specific rules for best results
- Use this as a reference for the subagent driven development approach

---
*Converted from Claude Code Skill: subagent-driven-development*
*Source: subagent driven development skill*