adversarial-debate-truthseeking

adversarial-debate-truthseeking is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 99 tokens per session (1,251 once invoked), scanned A, a copy of adversarial-debate-truthseeking, Apache-2.0.

A structured debate method for testing whether a claim can be checked against evidence. One role makes the claim as testable as possible, another looks for a result that would disprove it, and a judge labels it broken, supported, or impossible to test.

In plain words
What is it for?
Reviewing research claims, proposed explanations, and technical assumptions for clear tests and possible counterexamples.
Why use it?
It separates truth testing from persuasive argument, so claims cannot appear strong merely because they are vague or difficult to challenge.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing research claims, proposed explanations, and technical assumptions for clear tests and possible counterexamples.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/adversarial-debate-truthseeking
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 adversarial-debate-truthseeking
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 adversarial-debate-truthseeking

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/adversarial-debate-truthseeking"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/adversarial-debate-truthseeking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,251 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 91% copy Near-identical to another mod 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 $0.00099 $0.01251
Opus 5 $0.00049 $0.00626
Sonnet 5 $0.00020 $0.00250
Haiku 4.5 $0.00010 $0.00125

Measured 10d ago against content hash abcdac60b2b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adversarial-debate-truthseeking 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.

Origin

This is a copy

91% identical to adversarial-debate-truthseeking — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/adversarial-debate-truthseeking/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Debate (Truth-Seeking Variant)

A retuning of classic critic-defender-judge debate. The classic version asks "which side argued better?" and outputs a survival/resilience verdict — a persuasiveness metric. That is wrong for research: a claim can win a debate by being slippery (un-pin-down-able) while being scientifically empty. This variant changes the roles and the judge's job so the debate produces a falsifiability classification, not a winner.

What changed from the original (multiagent-debate)

Element Original (publication) This variant (truth-seeking)
Defender's job Make the claim look strong / survive State the claim in its MOST falsifiable form — maximize what it forbids
Critic's job Find weaknesses to score against Find one concrete observation/computation that would refute it
Judge's verdict Winner + resilience score Bucket: BROKEN / CORROBORATED / UNFALSIFIABLE
Success Artifact survives We learn whether the claim is even testable, and if so whether it holds
Slippery claim Wins (un-attackable) Flagged UNFALSIFIABLE (worst outcome)

Roles

Defender (steelman-to-falsifiable)

The defender does NOT defend the claim as comfortable or vague. The defender's sole job is to restate the claim in the sharpest, most-forbidding form that is still faithful to what we actually meant. A claim of the form "the unification is elegant" is not a defendable form — it forbids nothing. "Under intervention X the law collapses to form A and NOT form B" is — it stakes out something an observation could contradict. If the defender cannot produce a forbidding form, that itself is the verdict (UNFALSIFIABLE) — the defender must report this honestly rather than retreat to vagueness.

Critic (refuter)

The critic does NOT accumulate debating points. The critic tries to produce ONE of: (a) a counterexample (a case the claim forbids but that occurs / could occur), (b) a derivation error (the claim does not follow from its stated premises), (c) a demonstration that the claim's "forbidden" set is empty (it forbids nothing → UNFALSIFIABLE). The critic must commit to a specific refuter before arguing, to prevent goalpost-shifting.

Read the full file on GitHub · 62 lines

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 · 62 lines · 99 tokens per session scan A abcdac60b2b0

Subscribe to this mod's changes

adversarial-debate-truthseeking is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,251 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to adversarial-debate-truthseeking, differing in 19 lines, and is treated as a copy.

Related

Other skills, from other repositories

tournament-judge

Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…

alextverdyy/tournament-judge · 105 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens

shogun-screenshot

A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.

yohey-w/multi-agent-shogun · 149 tokens

creating-skills

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…

redai-infra/Relax · 70 tokens