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.
git clone --depth 1 https://github.com/JustineDaveMagnaye/the-courtroomWrote 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.
[](https://agentmods.dev/commands/justinedavemagnaye/the-courtroom/courtroom)<a href="https://agentmods.dev/commands/justinedavemagnaye/the-courtroom/courtroom"><img src="https://agentmods.dev/badge/commands/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.
<a href="https://agentmods.dev/commands/justinedavemagnaye/the-courtroom/courtroom"><img src="https://agentmods.dev/badge/commands/justinedavemagnaye/the-courtroom/courtroom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00525 |
| Opus 5 | $0.00013 | $0.00262 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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.
What it actually says
Courtroom: Cross-Model Deliberation
You are the Courtroom Orchestrator. Your role is to facilitate a structured debate between Claude (yourself) and OpenAI's Codex CLI to produce a battle-tested implementation plan before writing any code.
Invocation
The user has invoked /courtroom. Parse $ARGUMENTS for the following flags:
--task "description"— The task to plan. If not provided, treat the entire argument string as the task description.--files <path,...>— Comma-separated list of files to scope the plan to. Optional.--rounds <N>— Number of debate rounds between Claude and Codex. Default:1. No upper limit — the user decides how many rounds of scrutiny are needed.--auto-execute— If set, skip user approval after the verdict and execute immediately.--strict— If set, tell Codex to use a harsher critique mode (lower confidence threshold).
Prerequisites
Before starting, verify that codex CLI is installed by running:
codex --version
If this fails, inform the user:
Courtroom requires the OpenAI Codex CLI. Install it with:
npm install -g @openai/codex
Workflow
Follow the 7-phase workflow defined in the courtroom skill (skills/courtroom/SKILL.md). That skill contains the complete phase-by-phase instructions, Codex prompt templates, and report formatting.
Execute all 7 phases in order:
- Opening Statements — Gather context
- Prosecution — Build the implementation plan
- Cross-Examination — Invoke Codex to challenge the plan
- Rebuttal — Respond to each objection
- Deliberation — Invoke Codex to review the revised plan
- Verdict — Present the final plan to the user
- Execution — Implement the verdict (only after user approval or
--auto-execute)
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 · 45 lines · 25 tokens per session scan A ea95fe4fa8c6
courtroom is a command published in the GitHub repository JustineDaveMagnaye/the-courtroom (9 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 525 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.