subagent-driven-development skill

Subagent-Driven Development

Overview

Execute implementation plans by dispatching fresh subagents per task with systematic two-stage review.

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

When to Use

Use this skill when:

You have an implementation plan (from writing-plans skill or user requirements)
Tasks are mostly independent
Quality and spec compliance are important
You want automated review between tasks

vs. manual execution:

Fresh context per task (no confusion from accumulated state)
Automated review process catches issues early
Consistent quality checks across all tasks
Subagents can ask questions before starting work

The Process

1. Read and Parse Plan

Read the plan file. Extract ALL tasks with their full text and context upfront. Create a todo list:

# Read the plan
read_file("docs/plans/feature-plan.md")

# Create todo list with all tasks
todo([
    {"id": "task-1", "content": "Create User model with email field", "status": "pending"},
    {"id": "task-2", "content": "Add password hashing utility", "status": "pending"},
    {"id": "task-3", "content": "Create login endpoint", "status": "pending"},
])

Key: Read the plan ONCE. Extract everything. Don't make subagents read the plan file — provide the full task text directly in context.

2. Per-Task Workflow

For EACH task in the plan:

Step 1: Dispatch Implementer Subagent

Use delegate_task with complete context:

delegate_task(
    goal="Implement Task 1: Create User model with email and password_hash fields",
    context="""
    TASK FROM PLAN:
    - Create: src/models/user.py
    - Add User class with email (str) and password_hash (str) fields
    - Use bcrypt for password hashing
    - Include __repr__ for debugging

    FOLLOW TDD:
    1. Write failing test in tests/models/test_user.py
    2. Run: pytest tests/models/test_user.py -v (verify FAIL)
    3. Write minimal implementation
    4. Run: pytest tests/models/test_user.py -v (verify PASS)
    5. Run: pytest tests/ -q (verify no regressions)
    6. Commit: git add -A && git commit -m "feat: add User model with password hashing"

    PROJECT CONTEXT:
    - Python 3.11, Flask app in src/app.py
    - Existing models in src/models/
    - Tests use pytest, run from project root
    - bcrypt already in requirements.txt
    """,
    toolsets=['terminal', 'file']
)

Step 2: Dispatch Spec Compliance Reviewer

After the implementer completes, verify against the original spec:

delegate_task(
    goal="Review if implementation matches the spec from the plan",
    context="""
    ORIGINAL TASK SPEC:
    - Create src/models/user.py with User class
    - Fields: email (str), password_hash (str)
    - Use bcrypt for password hashing
    - Include __repr__

    CHECK:
    - [ ] All requirements from spec implemented?
    - [ ] File paths match spec?
    - [ ] Function signatures match spec?
    - [ ] Behavior matches expected?
    - [ ] Nothing extra added (no scope creep)?

    OUTPUT: PASS or list of specific spec gaps to fix.
    """,
    toolsets=['file']
)

If spec issues found: Fix gaps, then re-run spec review. Continue only when spec-compliant.

Step 3: Dispatch Code Quality Reviewer

After spec compliance passes:

delegate_task(
    goal="Review code quality for Task 1 implementation",
    context="""
    FILES TO REVIEW:
    - src/models/user.py
    - tests/models/test_user.py

    CHECK:
    - [ ] Follows project conventions and style?
    - [ ] Proper error handling?
    - [ ] Clear variable/function names?
    - [ ] Adequate test coverage?
    - [ ] No obvious bugs or missed edge cases?
    - [ ] No security issues?

    OUTPUT FORMAT:
    - Critical Issues: [must fix before proceeding]
    - Important Issues: [should fix]
    - Minor Issues: [optional]
    - Verdict: APPROVED or REQUEST_CHANGES
    """,
    toolsets=['file']
)

If quality issues found: Fix issues, re-review. Continue only when approved.

Step 4: Mark Complete

todo([{"id": "task-1", "content": "Create User model with email field", "status": "completed"}], merge=True)

3. Final Review

After ALL tasks are complete, dispatch a final integration reviewer:

delegate_task(
    goal="Review the entire implementation for consistency and integration issues",
    context="""
    All tasks from the plan are complete. Review the full implementation:
    - Do all components work together?
    - Any inconsistencies between tasks?
    - All tests passing?
    - Ready for merge?
    """,
    toolsets=['terminal', 'file']
)

4. Verify and Commit

# Run full test suite
pytest tests/ -q

# Review all changes
git diff --stat

# Final commit if needed
git add -A && git commit -m "feat: complete [feature name] implementation"

Task Granularity

Each task = 2-5 minutes of focused work.

Too big:

"Implement user authentication system"

Right size:

"Create User model with email and password fields"
"Add password hashing function"
"Create login endpoint"
"Add JWT token generation"
"Create registration endpoint"

Red Flags — Never Do These

Start implementation without a plan
Skip reviews (spec compliance OR code quality)
Proceed with unfixed critical/important issues
Dispatch multiple implementation subagents for tasks that touch the same files
Let subagents "just read the plan" — paste full task context directly
Fix issues yourself instead of re-dispatching the reviewer
Skip the final integration review

Handling Issues

When spec review fails:

Read the reviewer's specific gaps
Dispatch a new implementer subagent with the gap list as additional context
Re-run spec review after fix
Do NOT proceed to quality review until spec passes

When quality review fails:

Read the reviewer's issue list
Fix critical and important issues (minor can be deferred)
Re-run quality review
Only proceed when APPROVED

When both fail:

Fix spec gaps FIRST
Then fix quality issues
Re-run both reviews
This is expensive — get the spec right on first pass

Parallelism

Tasks that touch completely different files can run in parallel using the batch mode:

delegate_task(tasks=[
    {"goal": "Implement User model", "context": "...", "toolsets": ["terminal", "file"]},
    {"goal": "Implement logging utility", "context": "...", "toolsets": ["terminal", "file"]},
])

Rules for parallel tasks:

No shared files between any pair of tasks
No dependencies on each other's output
Each still gets separate spec + quality review after ALL complete
If any fails, fix it before reviewing the rest

Context Window Management

Each subagent starts fresh — no conversation history carries over.

Must include in every dispatch:

Full task text from the plan (not "see plan file")
Exact file paths to create/modify
Relevant code snippets they need to know about
Project conventions (testing framework, style, etc.)
Previous task results if there's a dependency

Don't include:

The entire plan (only their specific task)
Unrelated project context
Conversational history

Tips

Start with the simplest task to validate the workflow
If first task has issues, fix the plan before continuing
Timebox: if a single task takes 3+ subagent attempts, stop and reconsider the task scope
Keep commit messages consistent: feat:, fix:, refactor:, test:, docs: