You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Multi-agent review pipeline after task completion #16
After Ralph completes PRD tasks, run a multi-agent review pipeline before declaring done.
Inspired by ralphex's 4-phase approach but simplified:
Phase 1: Ralph executes tasks (current behavior)
Phase 2: Review agents run in parallel (new)
Phase 3: Fix confirmed issues (new)
Review Agents
Run N review agents concurrently, each with a focused prompt:
quality — bugs, security, race conditions
testing — test coverage gaps, weak assertions
simplification — over-engineering, dead code
Each agent reviews the diff (not full codebase), reports findings. Then a fix pass addresses confirmed issues.
Why
This bridges Ralph and Willie into one flow. Instead of "run Ralph, then manually run Willie," the review is built into the build pipeline. Ralph builds → agents review → fixes applied → done.
Willie remains the standalone deep audit tool. This is a lightweight review pass — faster, scoped to changes only, fewer agents. Willie is the full codebase scan.
Activity
dominicnunez commentedon Feb 21, 2026
Closed as duplicate of #24 - RFC: Springfield Ultra