Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the…
5.7k▲
+17
changed todayA
tokens not measured
originalMIT
LoopX adapter for Claude Code: the loopx control-plane MCP (shouldrun / claimtask / completetask) + the /loopx setup command + statusline. The run loop is Claude Code's native /loop, driven by a .claude/loop.md that /loopx writes; the optional shouldrun PreToolUse gate (hooks/goalpolicy.py) is added deliberately v.
5.4k▲
+81 todayA
tokens not measured
originalApache-2.0
OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
Multi-agent development system with three specialized agents (PM, Dev, QA) coordinated through checklist methodology based on The Checklist Manifesto and Boeing's checklist engineering.
Run your work like an AI agency, from a single Notion board. Agents discuss, plan, and execute tasks in parallel with dependency ordering and model routing.