long-running-agent-skill
Autonomous end-to-end project building with parallel subagents
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install long-running-agent-skill?โผ
Run `npx skills add jarrodwatts/long-running-agent-skill --all -g -y` in your terminal to install this skill globally.
How to build a full project autonomously?โผ
This skill interviews you upfront about goals and architecture, then plans milestones and executes them autonomously using parallel subagents in isolated git worktrees.
Does it work with Claude Code and Codex?โผ
Yes. It uses the Agent tool with worktree isolation in Claude Code and subagent teams with workspace isolation in Codex, plus any runtime that reads markdown state files.
How does it keep code quality high?โผ
Every milestone goes through a ruthless architectural review cycle, with fix subagents addressing issues until approval or a maximum of three iterations.
What happens if the session gets interrupted?โผ
Persistent state files in the .agent/ folder record progress, decisions, and architecture state, so work resumes cleanly after interruptions or context compaction.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core