debate-judge

debate-judge is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 26 tokens per session (352 once invoked), scanned A, original, Apache-2.0.

A judge for debate exchanges that compares arguments and replies, scores their quality, and gives a round verdict. It is used as a separate agent so the judgment is not biased by taking part in the argument.

In plain words
What is it for?
Use it to judge a debate round between critics and defenders, decide which side performed better, assess confidence in the result, and record the main findings.
Why use it?
It turns an argument into a structured decision with per-argument scoring, confidence, and key findings instead of relying on an informal opinion.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to judge a debate round between critics and defenders, decide which side performed better, assess confidence in the result, and record the main findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/debate-judge
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 yogsoth-ai/stress-test --skill debate-judge
Clone the repo
git clone --depth 1 https://github.com/yogsoth-ai/stress-test

Made for: Claude Code, Codex.

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 debate-judge

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/debate-judge/github.svg)](https://agentmods.dev/skills/yogsoth-ai/stress-test/debate-judge)
Your own site
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/debate-judge"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/debate-judge/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.

agentmods 80×15 button for debate-judge

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/debate-judge"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/debate-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 352 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00352
Opus 5 $0.00013 $0.00176
Sonnet 5 $0.00005 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 10d ago against content hash d584a0d54e14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

debate-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 10d 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/debate-judge/SKILL.md · 55 lines

What it actually says

Debate Judge

Evaluates exchanges and produces round verdicts.

Execution

Subagent — spawned via subagent-spawning/spawn-agent.

Why Subagent

Judgment requires neutral stance isolated from both attack and defense reasoning. Dedicated context prevents bias from prior participation.

Input

  • attacks: Structured attacks from debate-critic
  • defenses: Structured defenses from debate-defender
  • round_number: Current round in the debate
  • judging_criteria: Specific criteria for this debate type

Output

  • round_verdict: Which side prevailed this round (critic/defender/draw)
  • scores: Per-attack scoring (attack quality, defense quality, net result)
  • confidence: Judge's confidence in artifact viability (0.0–1.0)
  • key_findings: Most important insights from this round

Budget

One unit = one round verdict.

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOP When to use
spawn-agent Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.
Files

What ships with it

1 file 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.

  1. 10d ago First seen · 55 lines · 26 tokens per session scan A d584a0d54e14

Subscribe to this mod's changes

debate-judge is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 352 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.