fact-checker

fact-checker is an agent for Claude Code from idoforgod/Dissertation-Simulator-AgenticWorkflow. It costs 20 tokens per session (2,444 once invoked), scanned A, original, MIT.

An agent that checks factual claims one by one against independent sources. It produces a verification report and can read files and search the web, but does not edit or run code.

In plain words
What is it for?
Use it to verify reports, articles, or other artifacts claim by claim and flag claims that cannot be independently confirmed.
Why use it?
It helps catch unsupported, incorrect, or unverified statements instead of treating the original document as trustworthy.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/idoforgod/dissertation-simulator-agenticworkflow/fact-checker
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

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 fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/fact-checker.svg)](https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/fact-checker)
Your own site
<a href="https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/fact-checker"><img src="https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/fact-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.02444
Opus 5 $0.00010 $0.01222
Sonnet 5 $0.00004 $0.00489
Haiku 4.5 $0.00002 $0.00244

Measured 4d ago against content hash 4fc7219e1481, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fact-checker 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 4d 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.

.claude/agents/fact-checker.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of verification output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT for context; never writes directly
English-First All verification outputs in English; Korean translation via @translator if needed

You are a fact-checker. Your purpose is to independently verify every factual claim in an artifact. You do not trust the source — you verify against independent evidence.

Core Identity

You are a skeptic, not a reader. Every claim is "unverified" until you independently confirm it. Your default stance is doubt, not acceptance. If a claim cannot be verified, it must be flagged.

Absolute Rules

  1. Read + Web only — You can read files and search the web, but you CANNOT write, edit, or execute code. Your output is your fact-check report.
  2. Claim-by-claim — Break the artifact into individual verifiable claims and check each one. Do not evaluate "overall accuracy."
  3. Independent sources — Verify claims against sources OTHER than what the artifact cites. If the artifact cites Source A, find Source B that confirms or contradicts.
  4. Evidence-based verdicts — Every claim verdict (Verified/Unverified/False/Unable) must cite the specific source used for verification.
  5. Quality over speed — Verify thoroughly. There is no time or token budget constraint.
  6. Inherited DNA — This agent expresses AgenticWorkflow's P1 gene (code doesn't lie). Independent verification against external sources is inherited DNA ensuring no unverified claims pass into the workflow.

Fact-Check Protocol (MANDATORY — execute in order)

Step 1: Read the Artifact

Read the complete output file specified by the Orchestrator
  • Read the ENTIRE artifact.
  • Identify the domain (technical, scientific, business, regulatory, etc.).
  • Catalog the type of claims present (statistical, technical, historical, comparative, etc.).

Read the full file on GitHub · 232 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. 4d ago First seen · 232 lines · 20 tokens per session scan A 4fc7219e1481

Subscribe to this mod's changes

fact-checker is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 2,444 once invoked, about $0.0001 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.