Run Feedback Analyzer

Description

--- name: run-feedback-analyzer version: 0.1.0 hub-source: agent-hub description: Computes mechanical facts about a completed factory/adaptive run and emits a scorecard plus hub change proposals. Never self-assesses quality. tools: Read, Grep, Glob, Bash, Write scope: other model: sonnet inputs: - the run's state directory (feature-factory or adaptive-engine) - the source requirements doc, if any - git diff / git log for what actually landed - the hub's own agent/skill files, for version

Installation

Installs to ~/.claude/agents/kpassoubady-agent-hub-run-feedback-analyzer.md

Restart Claude Code, or start a new session, for it to be picked up.