htxryan

Audit and set up a codebase for agentic AI development using the 16-principle manifesto

Reviews code for architectural compliance and design integrity

Injects mistake-derived test requirements into the TDD pipeline

Clusters similar lessons and synthesizes testable patterns

Reviews UI code for design quality against the build-great-things quality checklist. Conditional — only activates when the Verification Contract includes design_craft_check evidence.

Analyzes repository structure, conventions, and patterns

Decompose a large system specification into cook-it-ready epic beads via DDD bounded contexts

Reflect on the cycle and capture high-quality lessons for future sessions

Audit and set up a codebase for agentic AI development using the 16-principle manifesto

Reflect on the cycle and capture high-quality lessons for future sessions

Full-cycle orchestrator chaining all five phases with gates and controls

Multi-agent review with lesson-calibrated reviewers, runtime verification, and severity classification

Multi-phase test suite optimization with adversarial review

Team-based TDD execution with adaptive complexity and agent delegation

Record bite-sized, feature-focused walkthrough videos from the pearl demo library (docs/demos/). Each demo has its own scene script so it can be re-recorded individually. Keeps overlays (cursor, click pulse, keystrokes, region highlight) and ffmpeg captions from the original. Validates output before delivering.

Actively monitor a running compound-agent infinity loop, checking progress every N minutes (default 5). Reports epic status, current activity, and flags issues.

Reference for configuring, launching, and monitoring infinity loops and polish loops

Create a new operator subagent for a CLI tool and add its enforce-operator hook guard