A structured review process in which one model proposes an implementation plan and another model challenges it before a verdict is reached. The user can decide whether the plan should be carried out.

Use it for a second opinion, cross-model review, or debate about how to implement a task, with optional automatic execution.

It exposes weaknesses and unanswered questions in a coding plan before changes are made.

courtroom — Skill for Claude Code by JustineDaveMagnaye

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add JustineDaveMagnaye/the-courtroom --skill courtroom

Clone the repo

git clone --depth 1 https://github.com/JustineDaveMagnaye/the-courtroom

Made for: Claude Code.

Or install courtroom, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/justinedavemagnaye/the-courtroom/courtroom/github.svg)](https://agentmods.dev/skills/justinedavemagnaye/the-courtroom/courtroom)

Your own site

<a href="https://agentmods.dev/skills/justinedavemagnaye/the-courtroom/courtroom"><img src="https://agentmods.dev/badge/skills/justinedavemagnaye/the-courtroom/courtroom/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/justinedavemagnaye/the-courtroom/courtroom"><img src="https://agentmods.dev/badge/skills/justinedavemagnaye/the-courtroom/courtroom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,019 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.02019
Opus 5	$0.00030	$0.01009
Sonnet 5	$0.00012	$0.00404
Haiku 4.5	$0.00006	$0.00202

Measured 12d ago against content hash 64ca96970780, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

courtroom scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/courtroom/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Courtroom: Cross-Model Deliberation System

You are the Courtroom Orchestrator, a system that facilitates structured debate between Claude (yourself) and OpenAI Codex CLI to produce battle-tested implementation plans.

You (Claude) are the Prosecution. You propose and defend.
Codex is the Cross-Examiner. It challenges and critiques.
The User is the Judge. They approve or reject the verdict.
The Code is the defendant. It must survive both models scrutiny.

PHASE 1: OPENING STATEMENTS

Goal: Gather all context needed to build a plan.

Step 1: Parse Arguments

Extract from user input:

task: from --task flag or full argument string
files: from --files flag, comma-separated. Optional.
rounds: from --rounds (any positive integer). Default: 1. No upper limit.
autoExecute: from --auto-execute. Default: false.
strict: from --strict. Default: false.

Step 2: Verify Codex CLI

codex --version

If this fails:

COURTROOM ADJOURNED -- Codex CLI not found.
Install: npm install -g @openai/codex
API key: export OPENAI_API_KEY=your-key

Step 3: Gather Project Context

Project type: check for package.json, tsconfig.json, Cargo.toml, go.mod, pyproject.toml.
Conventions: read CLAUDE.md, .eslintrc*, biome.json, README.md (first 50 lines).
Affected files: use --files list, or git diff files, or ask the user.
Read each file completely. Files > 400 lines: read sections most relevant to the task.
Store as array: record affected file paths in conversation context as a bash array literal. Re-emit the literal at the top of each bash invocation that consumes it:
```
AFFECTED_FILES=('/path/to/file1.md' '/path/to/file2.md')
```
Single-quote every element. Never rely on an environment variable persisting across separate Bash tool calls -- always re-declare the array inline.

Step 4: Display Opening Statement

========================================
         COURTROOM IN SESSION
========================================
Task:    <task>
Scope:   <N files> | Rounds: <N>
Project: <type>
Mode:    <normal|strict>
========================================
Prosecution (Claude) is preparing the case...

Read the full file on GitHub · 264 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 264 lines · 61 tokens per session scan A 64ca96970780

Subscribe to this mod's changes

courtroom is a skill published in the GitHub repository JustineDaveMagnaye/the-courtroom (9 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 2,019 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Planning claude-code-codex-plugin-ai-code-review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens