subagent-driven-development

name	subagent-driven-development
description	Use when executing implementation plans with independent tasks in the current session
version	1.1.0
author	Hermes Agent (adapted from obra/superpowers)
license	MIT
metadata	{"hermes":{"tags":["delegation","subagent","implementation","workflow","parallel"],"platform":["cursor","codex","claude-code"],"related_skills":["writing-plans","requesting-code-review","test-driven-development"]},"triggers":["subagent","parallel","concurrent","multi task","delegate","background task","multiple things"]}
domain	agent-core
subdomain	planning
tokens	{"scan":315,"load":5640,"category":"detailed"}

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"

Large Content Generation Gotcha（2026-06-17 發現）

Subagents 生成大量結構化內容（如 500+ 行 JSON）時，output 容量限制會截斷結果。 解決方法：

• 每個 subagent 只做一個邏輯分塊（如 100 條問答），唔好叫佢一次過做 500 條
• merge 工作用 terminal script 做（read_file 食 entries → write_file 組合），唔好 dispatch 另一個 subagent 去做
• 如果 subagent 嘅 output 確定正確但被截斷，直接用終端機 script 拼返佢，唔好重新 dispatch
• 用 execute_code 喺 main context 做簡單嘅檔案組合工作，比 dispatch subagent 更可靠

Batch Content Generation Pattern（2026-06-17 建立）

當需要生成大量結構化內容（如題庫、詞典、設定檔），用呢個 pattern：

1. 分塊 dispatch：拆成 N 個獨立塊（如 5 個分類 × 100 條），每個 subagent 做一塊
2. 唔俾 reference file：context 入面淨係俾 format template + 內容範圍，唔好叫 subagent 讀取現有檔案做 reference
3. 明確禁止探索：context 第一句寫「唔需要探索檔案系統，直接生成內容就得」
4. merge 用 terminal script：所有 subagent 完成後，用 Python script 喺 main context 組合檔案，唔好再 dispatch merge subagent
5. 直接寫檔案 vs patch：subagent 可以直接用 write_file 完整覆蓋檔案，比 read_file→patch 更可靠（patch 要搵 exact match string，容易失敗）

Subagent Context Size Gotcha（2026-06-17 發現）

Subagent 嘅 context 如果太大（如包含 100 條問答做 reference），佢會用大量 iterations 去探索檔案系統而唔係直接生成內容。 解決方法：

• context 要精準：淨係俾 format template + 內容範圍，唔好俾完整 reference file
• 明確寫「唔需要探索檔案系統，直接生成內容就得」
• toolsets 唔好俾 'file' 如果 subagent 唔需要讀寫檔案 — 淨係俾 terminal 寫 output

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
• Make subagent read the plan file (provide full text in context instead)
• Skip scene-setting context (subagent needs to understand where the task fits)
• Ignore subagent questions (answer before letting them proceed)
• Accept "close enough" on spec compliance
• 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 PASS (wrong order)
• Move to next task while either review has open issues

Handling 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 subagent (or a new one) fixes them
• Reviewer reviews again
• Repeat until approved
• Don't skip the re-review

If Subagent Fails a Task

• Dispatch a new fix subagent with specific instructions about what went wrong
• Don't try to fix manually in the controller session (context pollution)

Efficiency Notes

Why fresh subagent per task:

• Prevents context pollution from accumulated state
• Each subagent gets clean, focused context
• No confusion from prior tasks' code or reasoning

Why two-stage review:

• Spec review catches under/over-building early
• Quality review ensures the implementation is well-built
• Catches issues before they compound across tasks

Cost trade-off:

• More subagent invocations (implementer + 2 reviewers per task)
• But catches issues early (cheaper than debugging compounded problems later)

Integration with Other Skills

With writing-plans

This skill EXECUTES plans created by the writing-plans skill:

1. User requirements → writing-plans → implementation plan
2. Implementation plan → subagent-driven-development → working code

With test-driven-development

Implementer subagents should follow TDD:

1. Write failing test first
2. Implement minimal code
3. Verify test passes
4. Commit

Include TDD instructions in every implementer context.

With requesting-code-review

The two-stage review process IS the code review. For final integration review, use the requesting-code-review skill's review dimensions.

With systematic-debugging

If a subagent encounters bugs during implementation:

1. Follow systematic-debugging process
2. Find root cause before fixing
3. Write regression test
4. Resume implementation

Example Workflow

[Read plan: docs/plans/auth-feature.md]
[Create todo list with 5 tasks]

--- Task 1: Create User model ---
[Dispatch implementer subagent]
  Implementer: "Should email be unique?"
  You: "Yes, email must be unique"
  Implementer: Implemented, 3/3 tests passing, committed.

[Dispatch spec reviewer]
  Spec reviewer: ✅ PASS — all requirements met

[Dispatch quality reviewer]
  Quality reviewer: ✅ APPROVED — clean code, good tests

[Mark Task 1 complete]

--- Task 2: Password hashing ---
[Dispatch implementer subagent]
  Implementer: No questions, implemented, 5/5 tests passing.

[Dispatch spec reviewer]
  Spec reviewer: ❌ Missing: password strength validation (spec says "min 8 chars")

[Implementer fixes]
  Implementer: Added validation, 7/7 tests passing.

[Dispatch spec reviewer again]
  Spec reviewer: ✅ PASS

[Dispatch quality reviewer]
  Quality reviewer: Important: Magic number 8, extract to constant
  Implementer: Extracted MIN_PASSWORD_LENGTH constant
  Quality reviewer: ✅ APPROVED

[Mark Task 2 complete]

... (continue for all tasks)

[After all tasks: dispatch final integration reviewer]
[Run full test suite: all passing]
[Done!]

Remember

Fresh subagent per task
Two-stage review every time
Spec compliance FIRST
Code quality SECOND
Never skip reviews
Catch issues early

Quality is not an accident. It's the result of systematic process.