Kanevry

Skill Applied Judge — Development agent for Claude Code

Development community

Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each selected skill was actually APPLIED and whether its work COMPLETED.

How to install Skill Applied Judge

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

Terminal

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

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

What Skill Applied Judge does

name: skill-applied-judge description: 'Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each selected skill was actually APPLIED and whether its work COMPLETED. Dispatched read-only by scripts/lib/skill-judge.mjs::runSkillJudge as Haiku with a bounded per-call budget. RETURNS one fenced json block of advisory per-skill judgments; the coordinator writes them. Read-only by contract — never writes files. Advisory-only — output never gate

Alternatives in Development

Verify Claim Faithfulness — A verification agent that independently checks, at the sentence level, whether each cited source actually SUPP 134 ★
Robin — Read-only, skeptical evidence auditor for a Superloopy criterion 109 ★
Constraint Check — Internal affairs auditor — checks whether HARD-GATEs and constraints were actually followed during workflow 85 ★