subagent-driven-development

Files (1)

• SKILL.md

SKILL.md (first lines)

> **Pipeline position:** stage 3 of 3 — see [`reference/pipeline-flow.md`](../../reference/pipeline-flow.md).

# Subagent-Driven Development

If the Experimental claude team is available ask if we should run as a team. If yes then execute as a team with relevant team members in the loop. Always have at least one member acting as devils advocate when reviewing the implementers work separate from the code quality reviewer.

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. 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

## 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)

## Source of scope

The plan is in context but if needed a version should also have been saved in .claude-control/plans
The active goal should have `workflow_stage: plan_ready` and `plan_path` pointing at that approved file. Read that file and extract tasks directly from it. If the goal is not `plan_ready`, or `plan_path` is missing/unreadable, stop with a clear blocked state.

## The Process

```dot
digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./reference/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 (./reference/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 (./reference/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 superpowers:finishing-a-development-branch in PR-ready mode" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./reference/implementer-prompt.md)";
    "Dispatch implementer subagent (./reference/implementer-prompt.md)" -> "Implementer subagent asks questions?";
    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Dispatch implementer subagent (./reference/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 (./reference/spec-reviewer-prompt.md)";
    "Dispatch spec reviewer subagent (./reference/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 (./reference/spec-reviewer-prompt.md)" [label="re-review"];
    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./reference/code-quality-reviewer-prompt.md)" [label="yes"];
    "Dispatch code quality reviewer subagent (./reference/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 (./reference/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 (./reference/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 superpowers:finishing-a-development-branch in PR-ready mode";
}
```

## Completion Gate

After all tasks pass review, commit all implementation work, push the branch, and open an implementation PR. This skill ends with:

```yaml
metadata:
  workflow_stage: implementation_pr_open
  implementation_pr_url: <url>
  implementation_pr_number: <number>
```

Do not offer local merge, discard, or automatic goal completion as the normal path. Human review and PR merge are the acceptance gate; after the implementation PR merges, the goal may move to `done`.

## Model Selection

Use the least powerful model that can handle each role to conserve cost and increase speed.

**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.

**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.

**Architecture, design, and review tasks**: use the most capable available model.

**Task complexity signals:**

- Touches 1-2 files with a complete spec → cheap model
- Touches multiple files with integration concerns → standard model
- Requires design judgment or broad codebase understanding → most capable model

From Fleron/Claude-plugins, MIT.

More from Fleron/Claude-plugins