subagent-driven-development

name	subagent-driven-development
description	Use when executing implementation plans with independent tasks in the current session

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.

Why subagents: Delegate tasks to specialized agents with isolated context. By precisely crafting their instructions, you ensure they stay focused. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

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

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete.

When to Use

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"];
}

The Process

digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent" [shape=box];
        "Implementer asks questions?" [shape=diamond];
        "Answer questions" [shape=box];
        "Implementer implements, tests, commits, self-reviews" [shape=box];
        "Dispatch spec reviewer subagent" [shape=box];
        "Spec reviewer: code matches spec?" [shape=diamond];
        "Implementer fixes spec gaps" [shape=box];
        "Dispatch code quality reviewer subagent" [shape=box];
        "Code quality reviewer approves?" [shape=diamond];
        "Implementer fixes quality issues" [shape=box];
        "Mark task complete in TodoWrite" [shape=box];
    }

    "Read plan, extract all tasks, create TodoWrite" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final code reviewer for entire implementation" [shape=box];
    "Use finishing-a-development-branch skill" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract all tasks, create TodoWrite" -> "Dispatch implementer subagent";
    "Dispatch implementer subagent" -> "Implementer asks questions?";
    "Implementer asks questions?" -> "Answer questions" [label="yes"];
    "Answer questions" -> "Dispatch implementer subagent";
    "Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
    "Implementer implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent";
    "Dispatch spec reviewer subagent" -> "Spec reviewer: code matches spec?";
    "Spec reviewer: code matches spec?" -> "Implementer fixes spec gaps" [label="no"];
    "Implementer fixes spec gaps" -> "Dispatch spec reviewer subagent" [label="re-review"];
    "Spec reviewer: code matches spec?" -> "Dispatch code quality reviewer subagent" [label="yes"];
    "Dispatch code quality reviewer subagent" -> "Code quality reviewer approves?";
    "Code quality reviewer approves?" -> "Implementer fixes quality issues" [label="no"];
    "Implementer fixes quality issues" -> "Dispatch code quality reviewer subagent" [label="re-review"];
    "Code quality reviewer approves?" -> "Mark task complete in TodoWrite" [label="yes"];
    "Mark task complete in TodoWrite" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent" [label="yes"];
    "More tasks remain?" -> "Dispatch final code reviewer for entire implementation" [label="no"];
    "Dispatch final code reviewer for entire implementation" -> "Use finishing-a-development-branch skill";
}

Model Selection

Use the least powerful model that can handle each role:

• Mechanical tasks (isolated functions, clear specs, 1-2 files): cheap/fast model
• Integration tasks (multi-file coordination, pattern matching): standard model
• Architecture/review tasks: most capable model

Handling Implementer Status

DONE: Proceed to spec compliance review.

DONE_WITH_CONCERNS: Read concerns before proceeding. If about correctness/scope, address first.

NEEDS_CONTEXT: Provide missing context and re-dispatch.

BLOCKED: Assess the blocker:

1. Context problem → provide more context, re-dispatch
2. Needs more reasoning → re-dispatch with more capable model
3. Task too large → break into smaller pieces
4. Plan is wrong → escalate to the human

Implementer Prompt Template

Brief the implementer subagent with:

• Full task text (extracted from plan — never make them read the plan file)
• Scene-setting context: which codebase, what's been built so far, where this task fits
• TDD requirement: write failing test first, then implement
• Self-review requirement before reporting done
• Report status: DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED

Reviewer Prompt Templates

Spec reviewer: Given the task spec and git diff, does the implementation cover everything in the spec with nothing extra? Report: ✅ compliant or ❌ with specific gaps/extras.

Code quality reviewer: Review code quality against standards. Use requesting-code-review skill's template for full checklist. Report: ✅ approved or issues (Critical / Important / Minor).

Red Flags

Never:

• Start implementation on main/master branch without explicit user consent
• 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
• Accept "close enough" on spec compliance
• Start code quality review before spec compliance is ✅ (wrong order)
• Move to next task while either review has open issues

Integration

• using-git-worktrees — ensures isolated workspace
• writing-plans — creates the plan this skill executes
• requesting-code-review — code review template for reviewer subagents
• finishing-a-development-branch — complete development after all tasks