source_verification_agent

source_verification_agent is an agent for Claude Code from tuoxie2046/claude-code-research-skills. It costs 22 tokens per session (2,357 once invoked), scanned C, original, no licence file.

An agent that checks evidence and claims used in research. It also looks for predatory publications, which are outlets that may charge authors without providing reliable scholarly review.

In plain words
What is it for?
It is for grading research evidence, checking factual claims, and screening publications before they enter a research workflow.
Why use it?
It helps reduce the risk of using weak evidence, misleading claims, or unreliable research sources.

Agent for Claude Code

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

Part of the academic-research-skills plugin — 4 skills, 14 commands, 35 agents, 2 hooks shipped together

Good fit It is for grading research evidence, checking factual claims, and screening publications…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tuoxie2046/claude-code-research-skills/source_verification_agent
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/tuoxie2046/claude-code-research-skills

Made for: Claude Code.

Or install academic-research-skills, the plugin that ships this one along with the rest of its 4 skills, 14 commands, 35 agents, 2 hooks.

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 source_verification_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/tuoxie2046/claude-code-research-skills/source_verification_agent.svg)](https://agentmods.dev/agents/tuoxie2046/claude-code-research-skills/source_verification_agent)
Your own site
<a href="https://agentmods.dev/agents/tuoxie2046/claude-code-research-skills/source_verification_agent"><img src="https://agentmods.dev/badge/agents/tuoxie2046/claude-code-research-skills/source_verification_agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,357 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00022 $0.02357
Opus 5 $0.00011 $0.01179
Sonnet 5 $0.00004 $0.00471
Haiku 4.5 $0.00002 $0.00236

Measured 7d ago against content hash d6ce2b953bf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

source_verification_agent scanned grade C with 1 finding 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 7d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- canonical:instruction-data-boundary -->
plugins/academic-research-skills/deep-research/agents/source_verification_agent.md · 220 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 7d ago First seen · 220 lines · 22 tokens per session scan C d6ce2b953bf5

Subscribe to this mod's changes

source_verification_agent is an agent published in the GitHub repository tuoxie2046/claude-code-research-skills (5 stars, last pushed 2mo ago), with no licence file. It adds 22 tokens to every session and 2,357 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

quality-gates

Runs the repo's quality gates (lint, format, typecheck, dead-code, scoped tests) and returns a concise pass/fail report. Invoke only ONCE per slice / PR, immediately before commit — not mid-iteration, not after every file edit. Before delegating, the caller should run the project's auto-formatter on touched files…

Rijul1204/rashedul-agentic-engineering · 145 tokens

brainstorm-swarm:designer

Brainstorming persona — UX / Product Designer. Use when the swarm-protocol skill spawns parallel persona agents and a design perspective is needed. Asks about user flow, friction, accessibility, and aesthetic coherence.

viktorbezdek/skillstack · 50 tokens

shipkit-reviewer-planning

Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.

stefan-stepzero/shipkit · 32 tokens

ml-engineer

Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…

xvirobotics/metaskill · 81 tokens

ui-designer

Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibility. For example: adding a custom tab bar animation, implementing a skeleton loading view, auditing VoiceOver support…

xvirobotics/metaskill · 75 tokens

brainstorm-swarm:veteran

Brainstorming persona — Veteran / Lived Experience. Use when the swarm-protocol skill spawns parallel persona agents and pattern-matching against past failures would help. Brings war stories — "I've seen this before, here's what bit us" — with specific lessons grounded in past systems.

viktorbezdek/skillstack · 66 tokens