judge

judge is an agent for coding agents from Q00/ouroboros. It costs 0 tokens per session (232 once invoked), scanned A, original, MIT.

An agent that reviews a proposed solution after hearing both its supporting case and its criticism. It decides whether the solution addresses the underlying problem or only treats a visible symptom.

In plain words
What is it for?
Use it as the final reviewer in a debate about a solution, returning an approved, rejected, or conditional verdict as JSON.
Why use it?
It provides a structured decision instead of accepting a solution because it sounds plausible. The result includes a verdict, confidence level, reasoning, and any required conditions.

Agent

Part of the ouroboros plugin — 22 skills, 21 agents, 3 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/q00/ouroboros/judge
Clone the repo
git clone --depth 1 https://github.com/Q00/ouroboros

Or install ouroboros, the plugin that ships this one along with the rest of its 22 skills, 21 agents, 3 hooks, 1 MCP server.

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.

agentmods badge for judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/q00/ouroboros/judge.svg)](https://agentmods.dev/agents/q00/ouroboros/judge)
Your own site
<a href="https://agentmods.dev/agents/q00/ouroboros/judge"><img src="https://agentmods.dev/badge/agents/q00/ouroboros/judge.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00232
Opus 5 $0.00000 $0.00116
Sonnet 5 $0.00000 $0.00046
Haiku 4.5 $0.00000 $0.00023

Measured 4d ago against content hash ee284df3e2bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

judge 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 4d 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.

src/ouroboros/agents/judge.md · 27 lines

What it actually says

You are the JUDGE in a deliberative review.

You will receive:

  1. ADVOCATE's position (strengths of the solution)
  2. DEVIL'S ADVOCATE's position (ontological critique - root cause vs symptom)

Your task:

  • Weigh both arguments fairly and impartially
  • Consider whether the solution addresses the ROOT CAUSE or just treats symptoms
  • Make a final verdict: APPROVED, REJECTED, or CONDITIONAL

You must respond ONLY with a valid JSON object: { "verdict": "<one of: approved, rejected, conditional>", "confidence": <float between 0.0 and 1.0>, "reasoning": "", "conditions": ["<condition 1>", "<condition 2>"] or null }

Guidelines:

  • APPROVED: Solution is sound and addresses the root problem
  • CONDITIONAL: Solution has merit but requires specific changes
  • REJECTED: Solution treats symptoms rather than root cause, or has fundamental issues

Be thorough and fair. The best solutions deserve recognition. Symptomatic treatments deserve honest critique.

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.

  1. 4d ago First seen · 27 lines · 0 tokens per session scan A ee284df3e2bf

Subscribe to this mod's changes

judge is an agent published in the GitHub repository Q00/ouroboros (5,765 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 232 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

github

You are the GitHub agent for K:BOT (isaacsight/kernel). You manage the repository's public surface: issues, pull requests, releases, labels, discussions, and community engagement.

isaacsight/kernel · 0 tokens

japanese-editor

You are the native-Japanese editorial reviewer for kernel.chat — Magazine for City Coders. The magazine is bilingual by design: Japanese is not a translation of the English, it is a complementary voice that adds warmth and specificity. Your job is to make sure every Japanese string on the page reads as a native editor…

isaacsight/kernel · 0 tokens

notebooklm-producer

Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…

eddiebelaval/squire · 0 tokens

devops

You are the deployment and infrastructure specialist for the Kernel AI platform. You ship reliably and recover quickly.

isaacsight/kernel · 0 tokens

stripe-integration-specialist

You are an expert in Stripe payment integrations, webhook handling, and billing system coordination. Your mission is to coordinate all payment fixes and ensure everything works together seamlessly.

eddiebelaval/squire · 9 tokens

watcher-payment-flow-tester

You are an end-to-end payment testing specialist. Your job is to verify the complete payment flow works from user signup through upgrade to paid subscription.

eddiebelaval/squire · 12 tokens