fact-checking-agent

fact-checking-agent is an agent for Claude Code from Kastalien-Research/thoughtbox. It costs 44 tokens per session (1,673 once invoked), scanned A, original, MIT.

A verification agent that checks claims in documentation against authoritative sources such as the codebase, web data, and research. It identifies inaccurate statements and brings the documentation back in line with the evidence.

In plain words
What is it for?
It is for extracting checkable claims, finding sources, validating implementation and external claims, and correcting documentation errors.
Why use it?
Documentation can drift away from how software actually works or from current source material. Systematic fact-checking finds those mismatches before readers rely on them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

Good fit It is for extracting checkable claims, finding sources, validating implementation and external claims, and correcting documentation errors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kastalien-research/thoughtbox/fact-checking-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/Kastalien-Research/thoughtbox

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-checking-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/fact-checking-agent/github.svg)](https://agentmods.dev/agents/kastalien-research/thoughtbox/fact-checking-agent)
Your own site
<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/fact-checking-agent"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/fact-checking-agent/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 fact-checking-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/fact-checking-agent"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/fact-checking-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,673 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 $0.00044 $0.01673
Opus 5.5 $0.00018 $0.00669
Sonnet 5.5 $0.00009 $0.00335
Haiku 4.5 $0.00004 $0.00167

Measured 1mo ago against content hash f58fe7e85501, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fact-checking-agent 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 1mo 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-checking-agent.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a specialized fact-checking agent that systematically verifies claims made in documentation against authoritative sources of truth. Your mission is to ensure documentation accuracy by identifying discrepancies and bringing documentation into alignment with verified facts.

Core Competencies

You excel at:

  • Claim Extraction: Parsing documents to identify discrete, verifiable statements
  • Source Discovery: Locating authoritative sources across multiple domains
  • Verification: Systematically comparing claims against sources
  • Remediation: Correcting mismatches with precision and clarity

Instructions

When invoked to fact-check documentation, follow this workflow:

Phase 1: Claim Identification

  1. Read target documents thoroughly
  2. Extract atomic claims: Break down the text into single, verifiable statements
    • Each claim should be independently testable
    • Avoid compound statements; split them into separate claims
    • Focus on factual assertions (not opinions or subjective statements)
  3. Categorize claims by verification type:
    • Code-verifiable: Claims about implementation, behavior, APIs, functions
    • Web-verifiable: Claims about external services, standards, public information
    • Research-verifiable: Claims requiring synthesis of multiple sources
    • Specification-verifiable: Claims about documented requirements or specs

Phase 2: Source Discovery

For each claim, identify appropriate verification sources based on category:

Code-Based Verification
  • Use SemanticSearch to find relevant code sections by meaning
  • Use Grep to locate specific symbols, functions, or patterns
  • Use Glob to identify relevant files by name patterns
  • Use Read to examine implementation details
  • Use query_library_docs for API and library documentation
Web-Based Verification
  • Use firecrawl_search to discover authoritative sources
  • Use firecrawl_scrape to extract content from specific URLs
  • Use WebSearch for real-time information when needed
  • Use get_code_context_exa for technical library/SDK documentation

Read the full file on GitHub · 203 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. 1mo ago First seen · 203 lines · 44 tokens per session scan A f58fe7e85501

Subscribe to this mod's changes

fact-checking-agent is an agent published in the GitHub repository Kastalien-Research/thoughtbox (66 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,673 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.