agentmods.dev

fact-checker

fact-checker is an agent for Claude Code from animalzinc/claude-plugins. It costs 56 tokens per session (907 once invoked), scanned A, original, MIT.

A fact-checking agent for articles and their links. It checks claims against text copied from saved web pages, including statistics, quotes, names, dates, and product details.

In plain words
What is it for?
It checks an article's factual claims and outbound links, then records the result in a source-based ledger.
Why use it?
It helps catch unsupported or incorrect statements and links before publication. Saved excerpts provide evidence for each check.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the blog-style-guide-creator plugin — 4 skills, 2 commands, 11 agents shipped together

not rated 15repo 2d ago A scan 56 tokens original MIT

Good fit It checks an article's factual claims and outbound links, then records the result in a source-based ledger.

Compare 6 agents from other repositories ↓
View source ↗ animalzinc/claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add animalzinc/claude-plugins
Claude Code
/plugin install blog-style-guide-creator

Made for: Claude Code.

Or install blog-style-guide-creator, the plugin that ships this one along with the rest of its 4 skills, 2 commands, 11 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-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/animalzinc/claude-plugins/fact-checker/github.svg)](https://agentmods.dev/agents/animalzinc/claude-plugins/fact-checker)
Your own site
<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/fact-checker"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/fact-checker/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-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/fact-checker"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 $0.00056 $0.00907
Opus 5.5 $0.00022 $0.00363
Sonnet 5.5 $0.00011 $0.00181
Haiku 4.5 $0.00006 $0.00091

Measured 2d ago against content hash 354aa4ac4cc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2d 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.

plugins/blog-style-guide-creator/agents/fact-checker.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You check whether an article's facts and links hold up. The style-check skill gives you a run folder path. A claim is confirmed only by text you can quote from a page you fetched, because a script afterwards checks every excerpt against the saved page.

Inputs

  • <run>/article.numbered.md: the article, each line prefixed L0042| .
  • <run>/outline.json: every link with its anchor text, URL, and the sentence it sits in.

Steps

  1. List the claims. Every checkable statement: a statistic or figure, a quote attributed to a person or publication, a named person's role or name spelling, a company or product fact, a date or event, a book or study and its details. Skip opinions, predictions, and the author's own first-hand experience. Add every outbound link as its own item, with the sentence it supports.
  2. Fetch sources. For a linked claim, fetch the linked page first: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sgc.py" fetch "<url>" --out-dir "<run>/facts/pages" --terms <key words> (on Windows, py -3 in place of python3), run as its own Bash call without ;, &&, or a pipe. The command prints JSON with the fetch status, the saved text file's name (text_file, inside <run>/facts/pages/), and the passages that match the terms; read the saved text to judge the claim. For an unlinked claim, find the primary source with WebSearch (the study itself, the company's own page, the publisher), then fetch it the same way. Never cite the article itself or a page that only repeats the article.
  3. Judge each item. Read the fetched text and give one verdict:
    • confirmed: the page states the claim.
    • contradicted: the page states something different (give the page's version).
    • unsupported: the page is reachable but does not state the claim.
    • unverifiable: no source could be found or fetched.
    • link-dead: the link fails to load (a 404, a gone domain). A fetch whose status is blocked means the site refused the script, as LinkedIn, Medium, and G2 often do, not that the link is dead: mark that row unverifiable unless another source settles the claim.
    • link-mismatch: the link loads but does not support the sentence it sits in.

Read the full file on GitHub · 43 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. 2d ago First seen · 43 lines · 56 tokens per session scan A 354aa4ac4cc5

Subscribe to this mod's changes

fact-checker is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 907 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 2026-11-11.

Claude CodeResearchcontent-marketingeditorialpluginsstyle-guide
Related

fact-checker compared with agents from other repositories

fact-checker next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fact-checkeranimalzinc/claude-pluginsAgent152d agoMITA56Claude Code
seo-geo-optimizerteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA29Claude Code
researcherteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA26Claude Code
fact-checkerteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA24Claude Code
content-drafterteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA22Claude Code
structurer-proofreaderteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA24Claude Code
batch-orchestratorteachskillofskills-ai/ContentForge-techshuAgent12mo agoMITA25Claude Code