What is subagent-driven-development?
Use when executing implementation plans with independent tasks in the current session Source: hjewkes/agent-skills.
Use when executing implementation plans with independent tasks in the current session
Quickly install subagent-driven-development AI skill to your development environment via command line
Source: hjewkes/agent-skills.
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
Never: skip reviews, proceed with unfixed issues, dispatch parallel implementers to overlapping files (use wave plan file ownership to determine — parallel is encouraged when files don't overlap), paste full briefing text inline instead of pointing to briefing file, skip reading the manifest at wave boundaries, start code quality review before spec compliance passes.
Use when executing implementation plans with independent tasks in the current session Source: hjewkes/agent-skills.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/hjewkes/agent-skills --skill subagent-driven-developmentUse when executing implementation plans with independent tasks in the current session Source: hjewkes/agent-skills.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/hjewkes/agent-skills --skill subagent-driven-development Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/hjewkes/agent-skills