Install one, then just prompt in plain English. The FLOW.md fires the right skill at the right moment. No re-orchestration, no babysitting.
Featured
A quality-first harness for autonomous AI coding agents. It turns "the agent said it's done" into *"here's the proof — graded by an independent, default-FAIL checker."* Done is earned, not asserted.
@23ag1Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
@23ag1Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns…
@23ag1Run completely AUTONOMOUSLY — loop the FULL task engine over the Beads queue, a fresh `claude -p` per task, until the queue is empty. Same complete recipe as…
@23ag1Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best…
@23ag1Run all configured quality checks (lint, types, tests) in one pass with terse output — reports "clean" when green, and only the failing check's output when…
@23ag1Overview and entry point for the completely harness — a quality-first agent workflow unifying GSD (planning depth), Ralph (autonomous loop), and Beads (the…
@23ag1© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
