Courtroom Judge — Development agent for Claude Code
Courtroom role — reads the full record and the jury's votes, then either rules on the motion or asks precise follow-up questions for another hearing round.
How to install Courtroom Judge
Installs to ~/.claude/agents/rbarbaresco-skills-courtroom-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rbarbaresco/skills/HEAD/agents/courtroom-judge.md -o ~/.claude/agents/rbarbaresco-skills-courtroom-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Courtroom Judge does
name: courtroom-judge description: Courtroom role — reads the full record and the jury's votes, then either rules on the motion or asks precise follow-up questions for another hearing round. Spawned by the /courtroom workflow; not for general use. model: inherit # or sonnet / opus / haiku / fable effort: high # low / medium / high / xhigh / max disallowedTools: Edit, Write, NotebookEdit # read-only role
You are the judge in a
Alternatives in Development
- Owner Judge — Reviews proposed changes to VoiceStudio against the owner's documented standards 41.3k ★
- Yas Editor — Safely edits the YAS (Yet Another Statusline) renderer and its tests 241 ★
- Opengrep Rule Engineer — Expert in OpenGrep (FOSS Semgrep fork) and Semgrep rule authoring 50 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Courtroom Juror
Courtroom role — one specialist seat on the jury; rules on the motion strictly from the specialty named in the
Courtroom Defense
Courtroom role — argues that the motion should be denied or narrowed, finds what the prosecutor missed or got
Plan Polisher
Create or refresh an /aif-plan plan, critique it, and run one refinement round at most. The caller launches an
Frame Critic
Harsh, fresh-eyed motion director that scores one critique round of a promo video from its rendered review kit
Deep Rl Algorithms Curator
Curator for the deep RL algorithms lane of Reinforcement Learning Brain. Use when maintaining source coverage,
Interview Panel
Generates and stress-tests interview answers from three independent perspectives (hiring manager, peer enginee
Related Skills
AgentSuite
Seven role-specific reasoning agents that turn vague intent into precise operating artifacts
Switch Profile
Switch the active kit profile (two-role pipeline autopilot free) — rewrite the CLAUDE.md import line and .ai/k
Bench Run All
Agent-driven bench round for one size — drive the 2 variant folders + judge + capture, hands-off
