andrewstellman

Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.

Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.

Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.

Create a scheduled task that can be run on demand or automatically on an interval.

Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.

Orchestrate AI coding agents (or any job that appends JSON lines to a file) across many repos or branches from one agent session. Drives a disk-backed state machine one idempotent tick at a time - each tick the tick script reads workers' heartbeats, advances the state machine, and lists which workers to dispatch; the orchestrator launches them, prints the status table, and schedules the next tick (via ScheduleWakeup at cadence rung 1, or the foreground ticker at lower rungs). Dispatch is in-session subagents (rung 1) or detached shell workers. Runs until every job is terminal or a STOP file appears. Use when asked to run a batch of agent jobs, a benchmark plan, or multi-repo reviews.