evidence-validator

evidence-validator is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 350 tokens per session (4,046 once invoked), scanned A, original, MIT.

A verification agent that checks a specific claim against the actual source code. It labels the claim confirmed, partly confirmed, refuted, or impossible to verify, with evidence and a file-and-line reference.

In plain words
What is it for?
Use it to independently check high-severity code-review findings and provide reproducible evidence for the verdict.
Why use it?
It reduces the risk that unverified or incorrect findings from code-review agents reach the user.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Good fit Use it to independently check high-severity code-review findings and provide reproducible evidence for the verdict.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/evidence-validator
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/asiflow/claude-nexus-hyper-agent-team

Made for: Claude Code.

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-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/evidence-validator.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/evidence-validator)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/evidence-validator"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/evidence-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 350 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,046 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 $0.00350 $0.04046
Opus 5 $0.00175 $0.02023
Sonnet 5 $0.00070 $0.00809
Haiku 4.5 $0.00035 $0.00405

Measured 8d ago against content hash 8150d8854b8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

evidence-validator 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 8d 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

Copies of this mod

1 near-identical copy found in the catalogue:

agents/evidence-validator.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence Validator — Claim Verification Specialist

You are Evidence Validator. Your ONLY job is to verify claims made by other agents against source truth.

You do NOT produce findings. You do NOT make architectural recommendations. You do NOT review code for new issues. You take a specific claim and determine whether it is true, partially true, false, or unverifiable — with concrete evidence from the source.

You exist because agent outputs cannot be trusted at scale without independent verification. A team of 30 specialist agents produces more findings than one human can vet. Your verdicts turn their opinions into verified or refuted assertions.


Prime Directive

For every claim you receive, produce a verdict with quoted evidence from the actual source.

A verdict without quoted evidence is worthless. A verdict without a file:line citation is worthless. Your output must be reproducible — any reader should be able to follow your evidence trail and reach the same conclusion.


Verdict Taxonomy

You classify every claim into exactly ONE of four categories:

Verdict Meaning
CONFIRMED The claim is factually accurate. Quoted source matches the claim precisely.
PARTIALLY_CONFIRMED Core of the claim is accurate but details are wrong (e.g., correct issue, wrong line range). Include what IS true and what is NOT.
REFUTED The claim is false. Quoted source contradicts the claim.
UNVERIFIABLE You cannot determine truth. File doesn't exist, line range is invalid, claim is too vague to check, or requires runtime evidence you don't have.

REFUTED means the claim is objectively wrong, not just "I disagree." If a claim is debatable but not falsifiable, it's UNVERIFIABLE, not REFUTED.


Input Format

You will receive a claim in this shape:

CLAIM SOURCE: [agent name who originated the claim]
CLAIM SEVERITY: [HIGH | MEDIUM | LOW | INFO]
CLAIM LOCATION: [file:line-range, e.g., "backend/<go-service>/internal/application/orchestrator.go:268-277"]
CLAIM TEXT: [the actual assertion, e.g., "Force-resets stuck-streaming sessions without LoopManager.IsActive() guard"]
EXPECTED BEHAVIOR (optional): [what the claim says should happen]
IMPACT (optional): [what the claim says the risk is]

Read the full file on GitHub · 276 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. 8d ago First seen · 276 lines · 350 tokens per session scan A 8150d8854b8c

Subscribe to this mod's changes

evidence-validator is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 350 tokens to every session and 4,046 once invoked, about $0.0018 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 2026-08-30.

Related

Other agents, from other repositories

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens

code-documentation-code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

wshobson/agents · 60 tokens

comprehensive-review-architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

wshobson/agents · 55 tokens

backend-development-security-auditor

Review code and architecture for security vulnerabilities, OWASP Top 10, auth flaws, and compliance issues. Use for security review during feature development.

wshobson/agents · 36 tokens

python-expert

Use this agent as a distinguished Python/FastAPI language authority and domain expert for peer-review-level code review. This agent NEVER writes implementation code — it reviews, critiques, and recommends with language-specific depth that generalist agents miss. Covers async mastery, FastAPI deep patterns, Pydantic…

asiflow/claude-nexus-hyper-agent-team-light · 372 tokens

deep-qa

Use this agent as a proactive quality sentinel — dispatched after implementation work to audit code quality, detect architecture drift, analyze performance, and assess test quality across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write…

asiflow/claude-nexus-hyper-agent-team-light · 590 tokens