fact-check

fact-check is a command for Claude Code from bengous/claude-code-plugins. It costs 10 tokens per session (418 once invoked), scanned A, original, MIT.

A command that checks a factual claim against web sources.

In plain words
What is it for?
Use it to search for evidence, compare reliable sources, and report whether the claim is supported.
Why use it?
It helps reveal unsupported claims, conflicting evidence, or missing context.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the research-tools plugin — 1 skill, 4 commands, 2 agents shipped together

Good fit Use it to search for evidence, compare reliable sources, and report whether the claim is supported.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/bengous/claude-code-plugins/fact-check
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/bengous/claude-code-plugins

Made for: Claude Code.

Or install research-tools, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 2 agents.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/bengous/claude-code-plugins/fact-check.svg)](https://agentmods.dev/commands/bengous/claude-code-plugins/fact-check)
Your own site
<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/fact-check"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/fact-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00010 $0.00418
Opus 5 $0.00005 $0.00209
Sonnet 5 $0.00002 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 3d ago against content hash 9be6e5e92930, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fact-check 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 3d 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.

research-tools/commands/fact-check.md · 57 lines

What it actually says

Fact Check

Verify the following claim using web search:

Process

  1. Search broadly - Run multiple searches with different phrasings to find diverse sources
  2. Evaluate sources - Prioritize academic papers, official sources, and established journalism over blogs or social media
  3. Cross-reference - Look for independent confirmation across at least 2-3 sources
  4. Report - Present findings with clear sourcing

<parallel_search_guidance> When investigating a claim, run multiple WebSearch queries in parallel with different angles (e.g., the claim itself, key terms, potential counterarguments). This builds a more complete picture efficiently. </parallel_search_guidance>

Output Format

Verdict

<verdict_definitions>

  • Supported: Multiple reliable sources confirm the claim
  • Partially Supported: Core claim is accurate but contains inaccuracies or missing nuance
  • Disputed: Credible sources disagree; no clear consensus exists
  • Unsupported: No reliable sources confirm the claim, or evidence contradicts it
  • Unverifiable: Insufficient information available to assess the claim </verdict_definitions>

Evidence

Summarize key findings from sources (2-4 bullets)

Sources

List the sources consulted as markdown links

Guidelines

  • State your interpretation if the claim is ambiguous before searching
  • Note disagreements between sources and explain why you weighted certain sources higher
  • Separate factual claims from opinions or predictions
  • Ask for clarification only if the claim is too vague to search meaningfully
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. 3d ago First seen · 57 lines · 10 tokens per session scan A 9be6e5e92930

Subscribe to this mod's changes

fact-check is a command published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 418 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 2026-09-03.

Related

Other commands, from other repositories

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

hamr0/agentic-toolkit · 50 tokens

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

hamr0/agentic-toolkit · 62 tokens

branch-review

Command "branch-review" from hamr0/agentic-toolkit, covering guardrails, target — check the tree first, then interpret $arguments, effort level, stage 1 — general review and stage 2 — security (always full).

hamr0/agentic-toolkit · 0 tokens

slack-gif-creator

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

hamr0/agentic-toolkit · 57 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

hamr0/agentic-toolkit · 61 tokens

xlsx

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…

hamr0/agentic-toolkit · 96 tokens