subagent-driven-development

name	subagent-driven-development
description	Execute plans via delegate_task subagents (2-stage review).
version	1.1.0
author	Hermes Agent (adapted from obra/superpowers)
license	MIT
platforms	["linux","macos","windows"]
metadata	{"hermes":{"tags":["delegation","subagent","implementation","workflow","parallel"],"related_skills":["writing-plans","requesting-code-review","test-driven-development"]}}

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
• 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!]

Pitfalls — New Learnings from Session

delegate_task output truncation

Subagent returns can get silently truncated in long multi-file write sessions. The subagent's "done" self-report may not reflect all writes actually completed — verify file existence with terminal("ls ...") or terminal("find . -name 'X'") after a subagent completes. This is especially true when subagents write 10+ files.

Workaround: After any subagent that writes multiple files, add a verification step using terminal() in the controller session to confirm files exist and have expected content.

execute_code subprocess timeout with long foreground commands

execute_code subprocess runs cap out at ~5 minutes and stdout is capped at 50KB. Long foreground commands (pip installs, npm builds, test runs with verbose output) can exceed these limits silently. The subprocess will appear to succeed (RC 0) but output may be empty.

Workaround: For operations that may take >2 min or produce >50KB output, use terminal() instead of execute_code. If you must use execute_code, pipe output to a temp file and read it after.

Subagent self-report is not verification

Subagents claim "uploaded successfully" or "file written" may be wrong. Always verify external side-effects:

• HTTP POST/PUT → fetch the URL or check the response
• File writes → stat or ls the path
• Git commits → verify with git log -1

The skill already warns about this, but it bears repeating: a subagent's summary is a self-report, not a fact.

Git: never commit node_modules or large artifacts

Frontend node_modules/ (vendor packages), dist/ (build outputs), and .venv/ should never enter git. Committing node_modules/ creates multi-MB commits that are impractical to remove later.

Always: create .gitignore with at minimum:

node_modules/
dist/
.venv/
.pytest_cache/

Add it BEFORE the first commit. If you accidentally committed large dirs:

git rm -r --cached node_modules  # unstage
# Then commit .gitignore and push

Frontend TypeScript verification = build, not tests

For frontend React/TS projects, the equivalent of pytest tests/ is npm run build. TypeScript compilation via tsc catches type errors before runtime. There is no separate "test" step for type correctness — if npm run build succeeds, TypeScript is clean.

context construction: no plan file references

When dispatching, do NOT tell the subagent "read the plan file at X". Subagents cannot reliably read plan files (the controller session's working directory differs). Instead, extract the relevant plan section and embed the full task text in context. This is already in the skill but the session showed it in practice: I referenced plan files in subagent context and the subagent couldn't read them, forcing manual file reads by the controller.

Two-stage review order: spec FIRST, quality SECOND

This session confirmed the skill's rule: always do spec compliance review before code quality review. Quality review of non-compliant code is wasted effort. Check spec compliance first.

Subagent write conflicts: check before overwriting

When multiple subagents write to the same directory in the same phase, earlier subagents can overwrite later ones' content. The subagent that started first may have read stale/empty file state before writing. Mitigation: For concurrent writes to the same directory, add a "read existing files first" instruction to each subagent's goal. Verify final state with terminal("ls") after the phase.

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.

Further reading (load when relevant)

When the orchestration involves significant context usage, long review loops, or complex validation checkpoints, load these references for the specific discipline:

• references/context-budget-discipline.md — Four-tier context degradation model (PEAK / GOOD / DEGRADING / POOR), read-depth rules that scale with context window size, and early warning signs of silent degradation. Load when a run will clearly consume significant context (multi-phase plans, many subagents, large artifacts).
• references/gates-taxonomy.md — The four canonical gate types (Pre-flight, Revision, Escalation, Abort) with behavior, recovery, and examples. Load when designing or reviewing any workflow that has validation checkpoints — use the vocabulary explicitly so each gate has defined entry, failure behavior, and resumption rules.

Both references adapted from gsd-build/get-shit-done (MIT © 2025 Lex Christopherson).