# Subagent Driven Development

> Execute plans via autonomous agents with two-stage review per task. Use for complex implementations requiring quality gates.

- Skill: `oimiragieo/subagent-driven-development` (Agent Skill, multi-file: 10 files)
- Install (CLI): `npx skillmds@latest add oimiragieo/subagent-driven-development`
- Raw SKILL.md: https://api.skillmd.com/api/skills/oimiragieo/subagent-driven-development/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: oimiragieo (https://skillmd.com/u/oimiragieo)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/oimiragieo/subagent-driven-development

---


# Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

## When to Use

```dot
digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Stay in this session?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "executing-plans" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}
```

**vs. Executing Plans (parallel session):**

- Same session (no context switch)
- Fresh subagent per task (no context pollution)
- Two-stage review after each task: spec compliance first, then code quality
- Faster iteration (no human-in-loop between tasks)

## The Process

```dot
digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
        "Implementer subagent asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
        "Implementer subagent fixes spec gaps" [shape=box];
        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
        "Code quality reviewer subagent approves?" [shape=diamond];
        "Implementer subagent fixes quality issues" [shape=box];
        "Mark task complete in task-list (checklist)" [shape=box];
    }

    "Read plan, extract all tasks with full text, note context, create task-list (checklist)" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
    "Use verification-before-completion" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract all tasks with full text, note context, create task-list (checklist)" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
    "Code quality reviewer subagent approves?" -> "Mark task complete in task-list (checklist)" [label="yes"];
    "Mark task complete in task-list (checklist)" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
    "Dispatch final code reviewer subagent for entire implementation" -> "Use verification-before-completion";
}
```

## Prompt Templates

- `./implementer-prompt.md` - Dispatch implementer subagent
- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent

## Example Workflow

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

[Read plan file once: .claude/context/plans/feature-plan.md]
[Extract all 5 tasks with full text and context]
[Create task-list (checklist) with all tasks]

Task 1: Hook installation script

[Get Task 1 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: "Before I begin - should the hook be installed at user or system level?"

You: "User level (~/.config/agent-studio/hooks/)"

Implementer: "Got it. Implementing now..."
[Later] Implementer:
  - Implemented install-hook command
  - Added tests, 5/5 passing
  - Self-review: Found I missed --force flag, added it
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: Spec compliant - all requirements met, nothing extra

[Get git SHAs, dispatch code quality reviewer]
Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.

[Mark Task 1 complete]

Task 2: Recovery modes

[Get Task 2 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: [No questions, proceeds]
Implementer:
  - Added verify/repair modes
  - 8/8 tests passing
  - Self-review: All good
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: Issues:
  - Missing: Progress reporting (spec says "report every 100 items")
  - Extra: Added --json flag (not requested)

[Implementer fixes issues]
Implementer: Removed --json flag, added progress reporting

[Spec reviewer reviews again]
Spec reviewer: Spec compliant now

[Dispatch code quality reviewer]
Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)

[Implementer fixes]
Implementer: Extracted PROGRESS_INTERVAL constant

[Code reviewer reviews again]
Code reviewer: Approved

[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)
- Subagent can ask questions (before AND during work)

**vs. Executing Plans:**

- Same session (no handoff)
- Continuous progress (no waiting)
- Review checkpoints automatic

**Efficiency gains:**

- No file reading overhead (controller provides full text)
- Controller curates exactly what context is needed
- Subagent gets complete information upfront
- Questions surfaced before work begins (not after)

**Quality gates:**

- Self-review catches issues before handoff
- Two-stage review: spec compliance, then code quality
- Review loops ensure fixes actually work
- Spec compliance prevents over/under-building
- Code quality ensures implementation is well-built

**Cost:**

- More subagent invocations (implementer + 2 reviewers per task)
- Controller does more prep work (extracting all tasks upfront)
- Review loops add iterations
- But catches issues early (cheaper than debugging later)

## Red Flags

**Never:**

- Skip reviews (spec compliance OR code quality)
- Proceed with unfixed issues
- Dispatch multiple implementation subagents in parallel (conflicts)
- Make subagent read plan file (provide full text instead)
- Skip scene-setting context (subagent needs to understand where task fits)
- Ignore subagent questions (answer before letting them proceed)
- Accept "close enough" on spec compliance (spec reviewer found issues = not done)
- Skip review loops (reviewer found issues = implementer fixes = review again)
- Let implementer self-review replace actual review (both are needed)
- **Start code quality review before spec compliance is approved** (wrong order)
- Move to next task while either review has open issues

**If subagent asks questions:**

- Answer clearly and completely
- Provide additional context if needed
- Don't rush them into implementation

**If reviewer finds issues:**

- Implementer (same subagent) fixes them
- Reviewer reviews again
- Repeat until approved
- Don't skip the re-review

**If subagent fails task:**

- Dispatch fix subagent with specific instructions
- Don't try to fix manually (context pollution)

## Integration

**Required workflow skills:**

- **writing-plans** - Creates the plan this skill executes
- **verification-before-completion** - Complete development after all tasks

**Subagents should use:**

- **tdd** - Subagents follow TDD for each task

**Alternative workflow:**

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

## Iron Laws

1. **NEVER** spawn a subagent without including the full task text in the spawn prompt
2. **ALWAYS** run two-stage review per task: spec compliance first, then quality gate
3. **NEVER** reuse a subagent for multiple tasks — spawn a fresh agent per task
4. **ALWAYS** require subagents to call `TaskUpdate(completed)` before the orchestrator proceeds
5. **NEVER** mark orchestration complete until all subagent tasks pass both review stages

## Anti-Patterns

| Anti-Pattern                         | Why It Fails                                             | Correct Approach                                                           |
| ------------------------------------ | -------------------------------------------------------- | -------------------------------------------------------------------------- |
| Sparse spawn prompts                 | Subagent lacks context; produces incorrect output        | Include full task text, file paths, and constraints in every spawn prompt  |
| Skipping two-stage review            | Low-quality output reaches completion without validation | Always run spec compliance check then quality gate before accepting output |
| Reusing subagents for multiple tasks | State contamination between unrelated tasks              | Spawn a fresh subagent for each independent task                           |
| Not checking TaskUpdate completion   | Orchestrator advances before work is done                | Verify `TaskUpdate(completed)` from each subagent before proceeding        |
| Marking done before all stages pass  | Incomplete or failing tasks considered complete          | Only mark orchestration done when all tasks pass both review stages        |

## Memory Protocol (MANDATORY)

**Before starting:**
Read `.claude/context/memory/learnings.md`

**After completing:**

- New pattern -> `.claude/context/memory/learnings.md`
- Issue found -> `.claude/context/memory/issues.md`
- Decision made -> `.claude/context/memory/decisions.md`

> ASSUME INTERRUPTION: If it's not in memory, it didn't happen.