evidence-tournament

evidence-tournament is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 35 tokens per session (641 once invoked), scanned A, original, Apache-2.0.

A structured method for collecting and judging evidence for or against a claim. It uses separate researchers, critics, defenders, cross-examination, and a judge to assess relevance, reliability, freshness, and specificity.

In plain words
What is it for?
Use it when an artifact or decision needs evidence gathering, competing interpretations, challenges to sources, and a scored assessment of the final evidence.
Why use it?
It reduces one-sided conclusions by making supporting and opposing evidence visible and checking the quality of each source.

Skill for Claude CodeCodex

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

Good fit Use it when an artifact or decision needs evidence gathering, competing interpretations, challenges to sources, and a scored assessment of the final evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/evidence-tournament
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 evidence-tournament
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 evidence-tournament

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/evidence-tournament"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/evidence-tournament.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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 $0.00035 $0.00641
Opus 5 $0.00017 $0.00320
Sonnet 5 $0.00007 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 10d ago against content hash 75b4fc2bd9e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evidence-tournament 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/evidence-tournament/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence Tournament Tactic

Structured evidence competition — gather, present, cross-examine, and judge evidence quality.

Orchestration

  1. evidence-scout searches for evidence supporting the artifact's claims
  2. evidence-scout searches for evidence opposing the artifact's claims
  3. debate-critic presents opposing evidence as structured arguments
  4. debate-defender presents supporting evidence as counter-arguments
  5. cross-examination probes both evidence sets:
    • Source reliability assessment
    • Relevance to specific claims
    • Recency and applicability
    • Potential confounds or alternative interpretations
  6. debate-judge scores each piece of evidence and produces tournament bracket result

Evidence Quality Criteria

  • Relevance: Direct bearing on the claim (0.0–1.0)
  • Reliability: Source credibility and methodology (0.0–1.0)
  • Recency: Temporal applicability (0.0–1.0)
  • Specificity: How precisely it addresses the claim (0.0–1.0)

Subagents Dispatched

  • evidence-scout × 2 (pro and con evidence gathering)
  • debate-critic (opposing evidence presentation)
  • debate-defender (supporting evidence presentation)
  • cross-examination (evidence probing)
  • debate-judge (evidence scoring and verdict)

Termination Conditions

  • All claims have been evidenced and cross-examined
  • Evidence search budget exhausted (2/5/10 searches)
  • No further relevant evidence discoverable
  • Judge has scored all evidence pairs

Available SOPs

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

SOP When to use
cross-examination Probes defender responses for inconsistencies, logical gaps, and unsupported claims. Acts as follow-up interrogation after initial defense.
debate-critic Generates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses.
debate-defender Responds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms.
debate-judge Evaluates debate exchanges, adjudicates argument quality, and produces round verdicts with confidence scores and reasoning.
evidence-scout Searches for external evidence supporting or opposing specific claims. Returns structured evidence with source assessment and relevance scoring.

Read the full file on GitHub · 73 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 · 73 lines · 35 tokens per session scan A 75b4fc2bd9e5

Subscribe to this mod's changes

evidence-tournament is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 641 once invoked, about $0.0002 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.

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

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 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