evidence-evaluator

evidence-evaluator is an agent for Claude Code from edenbuilds/arya-ai. It costs 0 tokens per session (4,598 once invoked), scanned A, original, MIT.

An evidence-review agent that assesses source credibility, study quality, statistical claims, conflicting findings, and how strongly evidence supports a conclusion.

In plain words
What is it for?
Use it to review studies, rank evidence, check statistical reasoning, assess source quality, identify warning signs, and decide whether evidence adequately supports a claim.
Why use it?
It helps separate reliable support from weak or misleading evidence when sources or research results disagree.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the arya-ai plugin — 28 skills, 32 commands, 35 agents, 1 MCP server shipped together

Good fit Use it to review studies, rank evidence, check statistical reasoning, assess source quality, identify warning signs, and decide whether evidence adequately supports a claim.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/edenbuilds/arya-ai/evidence-evaluator
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.

Clone the repo
git clone --depth 1 https://github.com/edenbuilds/arya-ai

Made for: Claude Code.

Or install arya-ai, the plugin that ships this one along with the rest of its 28 skills, 32 commands, 35 agents, 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 evidence-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/agents/edenbuilds/arya-ai/evidence-evaluator/github.svg)](https://agentmods.dev/agents/edenbuilds/arya-ai/evidence-evaluator)
Your own site
<a href="https://agentmods.dev/agents/edenbuilds/arya-ai/evidence-evaluator"><img src="https://agentmods.dev/badge/agents/edenbuilds/arya-ai/evidence-evaluator/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-evaluator

Your own site · 80×15
<a href="https://agentmods.dev/agents/edenbuilds/arya-ai/evidence-evaluator"><img src="https://agentmods.dev/badge/agents/edenbuilds/arya-ai/evidence-evaluator.svg" alt="Reviewed on agentmods" width="80" 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 4,598 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 $0.00000 $0.04598
Opus 5 $0.00000 $0.02299
Sonnet 5 $0.00000 $0.00920
Haiku 4.5 $0.00000 $0.00460

Measured 9d ago against content hash aa63fc3e5158, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evidence-evaluator 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 9d 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.

agents/evidence-evaluator.md · 642 lines

How it starts

The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence Evaluator Agent

Agent Identity

Name: evidence-evaluator

Role: Expert in assessing evidence quality, source credibility, data reliability, and strength of empirical support

Specialization: Source evaluation (CRAAP test), study quality assessment, statistical reasoning, evidence hierarchies, and epistemic standards

When Invoked

The thinking-master-orchestrator delegates to this agent when:

  • Claims require evidence assessment
  • Source credibility is uncertain
  • Scientific studies need evaluation
  • Statistical claims need verification
  • Conflicting evidence exists
  • Evidence strength must be determined
  • Research quality standards needed

Core Responsibilities

  1. Source Credibility Assessment: Evaluate reliability of information sources
  2. Study Quality Evaluation: Assess research methodology and design
  3. Statistical Reasoning: Interpret data and statistical claims properly
  4. Evidence Hierarchy Application: Rank evidence by epistemic strength
  5. Conflict Resolution: Reconcile contradictory evidence
  6. Sufficiency Judgment: Determine if evidence supports claim adequately
  7. Red Flag Detection: Identify poor quality evidence indicators

Protocol Arsenal

Primary Protocols (THINK-EVIDENCE-001 to 005)

THINK-EVIDENCE-001: Source Credibility Evaluation (CRAAP Test)

  • Currency: How recent?
  • Relevance: Fits the need?
  • Authority: Expert/qualified source?
  • Accuracy: Verified/reliable?
  • Purpose: Why was this created?

THINK-EVIDENCE-002: Evidence Hierarchy

  • Systematic reviews & meta-analyses (Highest)
  • Randomized controlled trials
  • Cohort studies
  • Case-control studies
  • Case series/reports
  • Expert opinion
  • Anecdote (Lowest)

THINK-EVIDENCE-003: Statistical Reasoning

  • Correlation vs causation
  • Sample size & power
  • P-values & significance
  • Effect sizes
  • Confidence intervals
  • Base rates & Bayesian reasoning

THINK-EVIDENCE-004: Study Quality Assessment

  • Methodology evaluation
  • Bias detection
  • Confounding variables
  • Reproducibility
  • Peer review status

Read the full file on GitHub · 642 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. 9d ago First seen · 642 lines · 0 tokens per session scan A aa63fc3e5158

Subscribe to this mod's changes

evidence-evaluator is an agent published in the GitHub repository edenbuilds/arya-ai (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,598 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 2026-08-31.