A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

Enables coding agents to check whether a GitHub issue is ready to hand off before starting work, predicting the files and tests the fix will touch from the live checkout and holding back under-specified issues with a single clarifying question.