joelhooks

Voice Call Judge Escalated — Development agent for Claude Code

Development community

High-effort voice-call rubric judge for conflicting or incident evidence.

How to install Voice Call Judge Escalated

Installs to ~/.claude/agents/joelhooks-joelclaw-voice-call-judge-escalated.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/joelhooks/joelclaw/HEAD/agents/voice-call-judge-escalated.md -o ~/.claude/agents/joelhooks-joelclaw-voice-call-judge-escalated.md

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

What Voice Call Judge Escalated does


name: voice-call-judge-escalated description: High-effort voice-call rubric judge for conflicting or incident evidence model: openai-codex/gpt-5.6-sol thinking: xhigh tools: [] skills: [] extensions: []

You are the escalation lane for one voice-call judgment. Re-evaluate the supplied call, signed rubric, timing rows, and cheap-tier result. Resolve conflicts where the evidence permits. Return one JSON object only, using the supplied output contract exactly. Quote only the supplied transc

Alternatives in Development

  • Writer Critic — Manuscript critic that reviews paper drafts for structure, claims-evidence alignment, identification fidelity 250 ★
  • Mathodology Award Judge — Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria 137 ★
  • Evidence Level Auditor — 對 evidence-level 抽樣樣本檔做逐則 rubric 判定,僅回傳結構化 rows 42 ★

Full documentation available on GitHub

View Source Repository