subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

Model	Source	Category
opus	core	Collaboration

Tools: Read, Glob, Grep, Bash, Edit, Write, Task, Skill

Overview

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 indep

<details>
<summary><strong>Full Reference</strong></summary>

# 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.

**Mandatory Announcement — FIRST OUTPUT before anything else:**

┏━ ⚡ subagent-driven-development ━━━━━━━━━━━━━━━━┓ ┃ [one-line description of what plan you’re executing] ┃ ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛

No exceptions. Box frame first, then work.

**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

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 TodoWrite" [shape=box];
    }

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

    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "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 TodoWrite" [label="yes"];
    "Mark task complete in TodoWrite" -> "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 armadillo:finishing-a-development-branch";
}

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

Implementer Context Hints

When dispatching implementer subagents, include these efficiency hints in the prompt:

Selective tests: “Run only tests related to your changes, not the full suite”
Caching: “If installing dependencies, use npm ci (faster than npm install)”
Background long tasks: “Use run_in_background: true for test suites and builds”

Parallel Dispatch

When multiple tasks touch completely separate files with zero overlap, dispatch their implementer subagents in parallel for faster execution.

When to Parallelize

digraph parallel_decision {
    "Tasks share any files?" [shape=diamond];
    "Dispatch sequentially" [shape=box];
    "Dispatch in parallel" [shape=box];
    "Review independently as each completes" [shape=box];

    "Tasks share any files?" -> "Dispatch sequentially" [label="yes — even one shared file"];
    "Tasks share any files?" -> "Dispatch in parallel" [label="no overlap at all"];
    "Dispatch in parallel" -> "Review independently as each completes";
}

Safe to parallelize:

Tasks creating different new files (e.g., two new skill SKILL.md files in separate directories)
Tasks modifying completely different existing files (e.g., one edits update.js, another edits doctor.js)
Test prompt creation tasks (each creates distinct test files)

Never parallelize:

Tasks that both modify the same file (e.g., two tasks both editing skills.json)
Tasks where one depends on the output of another
Tasks that both modify CLAUDE.md or any shared config file

Parallel Review

When parallel implementers complete, run spec + code quality review for each independently. If one fails review and needs fixes, that doesn’t block the other’s review.

Example Workflow

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

[Read plan file once: .claude/docs/plans/feature-plan.md]
[Extract all 5 tasks with full text and context]
[Create TodoWrite 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/armadillo/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:

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 that touch the same files (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 ✅ (wrong order)
Move to next task while either review has open issues

Bug monitoring: Between tasks, check for any persistent Tasks created by implementer subagents that indicate bugs:

If bug Task found with fix → review worktree branch, merge if clean
If bug Task found without fix → note for later, continue execution
Follow .claude/rules/bug-discipline.md Phase 3 protocol

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:

armadillo:worktree - REQUIRED: Set up isolated workspace before starting
armadillo:writing-plans - Creates the plan this skill executes
armadillo:requesting-code-review - Code review template for reviewer subagents
armadillo:finishing-a-development-branch - Complete development after all tasks

Subagents should use:

armadillo:test-driven-development - Subagents follow TDD for each task

Alternative workflow:

armadillo:executing-plans - Use for parallel session instead of same-session execution