subagent-driven-development

Executes implementation plans by dispatching fresh subagents per task with two-stage review.

2|Updated Aug 15, 2025
One-click install
npx skills add https://github.com/Grupo-6-ADS-B/FittNutri --skill subagent-driven-development-grupo-6-ads-b
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Grupo-6-ADS-B/FittNutri/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/Grupo-6-ADS-B/FittNutri --skill subagent-driven-development-grupo-6-ads-b

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Executing a multi-task implementation plan in a single session often pollutes context, skips reviews, and lets errors compound. This Skill orchestrates plan execution by dispatching a fresh subagent for each task and enforcing a two-stage review (spec compliance, then code quality) after every task. ## Core Features & Use Cases - Fresh Subagent Per Task: Each task runs in an isolated subagent context with curated instructions, preventing context pollution and keeping the controller focused on coordination. - Two-Stage Review Gates: A spec compliance reviewer verifies the code matches requirements before a code quality reviewer assesses maintainability, with fix-and-re-review loops until approval. - Status-Based Escalation: Implementer subagents report DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, or BLOCKED, and the controller responds with more context, a more capable model, or task decomposition. - Use Case: Given a written implementation plan with five independent tasks, the controller extracts all tasks into a todo list, dispatches implementer and reviewer subagents sequentially, and finishes with a final whole-implementation code review before merging the branch. ## Quick Start Ask the AI to execute your implementation plan using subagent-driven development with a fresh implementer subagent and spec plus quality reviews for each task.

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 an implementation plan with subagents?

Read the plan once, extract all tasks with full text into a todo list, then dispatch a fresh implementer subagent per task with the complete task text and context. After each task, run a spec compliance review followed by a code quality review before marking it complete.

What is the difference between subagent-driven development and executing plans?

Subagent-driven development stays in the same session with fresh subagents per task and automatic two-stage reviews, enabling faster iteration. Executing plans runs in a parallel session with human-in-the-loop handoffs between tasks.

When should I not use subagent-driven development?

Avoid it when tasks are tightly coupled and cannot run independently, when no implementation plan exists yet, or when you prefer a parallel session workflow. Also never dispatch multiple implementer subagents in parallel due to conflict risk.

How do I handle a blocked or failing implementer subagent?

Check the reported status: for NEEDS_CONTEXT provide missing information and re-dispatch, for BLOCKED either re-dispatch with a more capable model, break the task into smaller pieces, or escalate to the human if the plan itself is wrong. Never force the same model to retry unchanged.

Which model should I use for each subagent role?

Use a fast cheap model for mechanical tasks touching 1-2 files with clear specs, a standard model for multi-file integration work, and the most capable model for architecture, design, and review tasks. Match model power to task complexity signals.