Kanevry

Eval Judge — Development agent for Claude Code

Development community

Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and session_id — the record's instruction-adherence and report-q.

How to install Eval Judge

Installs to ~/.claude/agents/kanevry-session-orchestrator-eval-judge.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Kanevry/session-orchestrator/HEAD/agents/eval-judge.md -o ~/.claude/agents/kanevry-session-orchestrator-eval-judge.md

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

What Eval Judge does

name: eval-judge description: "Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and session_id — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by scripts/lib/eval/judge.mjs::runEvalJudge with a bounded per-call budget. RETURNS one fenced json block of two advisory judge dimensions (instruction-

Alternatives in Development

Tool Reviewer — Use this agent when you need to review MCP tool implementations for correctness, adherence to patterns, and be 175 ★
Prose Polisher — Rewrites existing text to improve clarity, conciseness, flow, and adherence to academic writing principles 169 ★
Constraint Check — Internal affairs auditor — checks whether HARD-GATEs and constraints were actually followed during workflow 85 ★