subagent-driven-development

Execute implementation plans with isolated subagents and automated code review.

Updated Feb 17, 2026
One-click install
npx skills add https://github.com/tim-hub/role-based-skills --skill subagent-driven-development-tim-hub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/tim-hub/role-based-skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/tim-hub/role-based-skills --skill subagent-driven-development-tim-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Executes implementation plans while avoiding context pollution by dispatching a fresh subagent for each independent task and enforcing code-review quality gates so work progresses quickly without losing correctness.

Core Features & Use Cases

  • Per-task fresh subagents: Each task runs in a new, isolated agent to prevent state leakage and conflicting edits.
  • Test-driven implementation: Subagents are instructed to write tests, implement code, and verify results before committing.
  • Automated code review checkpoints: A dedicated code-review subagent evaluates each change (Critical/Important/Minor) and triggers fixes as needed.
  • Use Case: Execute a written development plan with multiple independent tasks (hooks, recovery modes, features) to iterate rapidly while preserving quality and traceability via git SHAs and final review.

Quick Start

Use the subagent-driven-development skill to run a plan file and execute each task with a fresh implementation subagent followed by an automated code review and any necessary fixes.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I prevent context pollution when executing multiple development tasks in one session?

To prevent context pollution, each independent task runs in a fresh, isolated subagent that prevents state leakage and conflicting edits, keeping iterative development fast and accurate.

Can I enforce test-driven development and code review checkpoints automatically during development workflows?

Yes, you can enforce TDD and code review by running a dedicated subagent that evaluates each change by severity and triggers fixes after tests are written and verified.

What is the best way to execute a written implementation plan with multiple independent tasks?

Executing an implementation plan is best handled by dispatching per-task subagents that run test-driven implementation, automated code review, and git SHA tracking before final branch finishing.

Does this development workflow approach work without external dependencies?

Yes, this subagent-driven development workflow operates with no external dependencies, requiring only a plan file to orchestrate independent tasks with fresh subagents and integrated quality gates.

When should I not use subagent-driven development for task orchestration?

Avoid subagent-driven development when tasks are highly interdependent rather than mostly independent, as the workflow relies on isolated subagents and separate quality gates designed for continuous iteration without conflicting edits.