subagent-driven-development

Name: subagent-driven-development
Availability: InStock
Author: zhanglongxiao111

Assigns each ASTRO task to a fresh agent and reviews outcomes for correctness and quality.

35|5|Updated Sep 20, 2025

Search Tags:#isolation #task decomposition #prompt templates #subagent-driven development #code quality review #spec compliance review #iterative implementation

Ready to run

npx skills add https://github.com/zhanglongxiao111/indesign-cli --skill subagent-driven-development-zhanglongxiao111

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/zhanglongxiao111/indesign-cli/tree/main/.codex/skills/subagent-driven-development
Command: npx skills add https://github.com/zhanglongxiao111/indesign-cli --skill subagent-driven-development-zhanglongxiao111

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you execute multi-step implementation plans in a session by delegating each independent task to a fresh subagent, reducing context pollution and improving outcome quality through structured review checkpoints.

Core Features & Use Cases

Fresh subagent per task: dispatches a specialized implementer subagent with isolated context so it won’t inherit prior session history.
Two-stage review after each task: runs a spec compliance review first, then a code quality review to catch missing requirements and maintain maintainability.
Clear status handling loop: supports DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, and BLOCKED with escalation rules to avoid “retry without changes”.
Role-based model selection guidance: recommends using cheaper models for mechanical work and more capable models for architecture/review/judgment tasks.

Quick Start

Use this skill when you have an implementation plan with mostly independent tasks and want to dispatch one fresh subagent per task, followed by spec compliance and code quality reviews.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I execute multi-step implementation plans without context pollution?▼

To execute multi-step implementation plans without context pollution, dispatch a fresh subagent per independent task with isolated context. This prevents prior session history from degrading outcome quality during iterative execution.

What is subagent-driven development for iterative task execution?▼

Subagent-driven development is a workflow pattern that executes multi-task implementation plans by dispatching fresh subagents per independent task. It applies to same-session development requiring spec verification, structured status handling, and maintainable code outcomes.

How do I verify spec compliance and maintainable code after each task?▼

Verify spec compliance and maintainable code by running a two-stage post-task review. Execute a spec compliance review first to catch missing requirements, then run a code quality review to ensure maintainability after each task.

How do I handle subagent status like BLOCKED or NEEDS_CONTEXT during task decomposition?▼

Handle subagent status during task decomposition using a clear status handling loop with escalation rules. Support DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, and BLOCKED statuses to avoid retrying tasks without making actual changes.

When should I use isolated subagents for complex development workflows?▼

Use isolated subagents for complex development workflows when you have an implementation plan with mostly independent tasks. It suits same-session development where tasks need iterative execution, spec verification, and maintainable code outcomes.

How do I select models for role-based prompting in subagent-driven development?▼

Select models for role-based prompting by using cheaper models for mechanical implementation work and more capable models for architecture, review, and judgment tasks. This optimizes cost while maintaining code quality review standards.