macanderson

Eval Agent — Project Management agent for Claude Code

Project Management community

Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness).

How to install Eval Agent

Installs to ~/.claude/agents/macanderson-agent-harness-eval-agent.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/macanderson/agent-harness/HEAD/agents/eval-agent.md -o ~/.claude/agents/macanderson-agent-harness-eval-agent.md

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

What Eval Agent does

name: eval-agent description: Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness). Use after any non-trivial task when the user wants a quality assessment. Produces structured scorecard with evidence and improvement suggestions. tools: ["Read", "Write", "Edit", "Grep", "Glob", "Bash"] model: sonnet

You are a quality evaluator for AI agent output. Your job is to assess agent responses against structured criteria, not to perfo

Alternatives in Project Management

Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
Grainulator — Autonomous research sprint subagent 87 ★
Ba — Business Analyst — deep requirement elicitation BEFORE planning or coding 85 ★