fact-checker

fact-checker is a skill for Claude Code, Codex from moonlight-lupin/agent-skills. It costs 49 tokens per session (2,765 once invoked), scanned A, original, MIT.

A workflow for checking one factual claim at a time against multiple independent sources. It compares supporting and conflicting evidence and gives a cited status such as verified, disputed, unverified, or outdated.

In plain words
What is it for?
Use it to verify a specific statement and produce a concise report with source passages, source comparisons, confidence, and citations.
Why use it?
It helps catch plausible-sounding claims that are wrong, copied from weak sources, contradicted by later information, or no longer current.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to verify a specific statement and produce a concise report with source passages, source comparisons, confidence, and citations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moonlight-lupin/agent-skills/fact-checker
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.

Any agent
npx skills add moonlight-lupin/agent-skills --skill fact-checker
Clone the repo
git clone --depth 1 https://github.com/moonlight-lupin/agent-skills

Made for: Claude Code, Codex.

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/skills/moonlight-lupin/agent-skills/fact-checker/github.svg)](https://agentmods.dev/skills/moonlight-lupin/agent-skills/fact-checker)
Your own site
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/fact-checker"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/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/skills/moonlight-lupin/agent-skills/fact-checker"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,765 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.02765
Opus 5 $0.00024 $0.01383
Sonnet 5 $0.00010 $0.00553
Haiku 4.5 $0.00005 $0.00277

Measured 11d ago against content hash 1574782672b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/verify.py, tests/test_verify.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/fact-checker/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact Checker

Overview

Fact Checker is a targeted verification workflow for one factual assertion at a time. It exists because agents often produce claims that sound plausible but may be hallucinated, copied from a weak source, contradicted by later data, or stale after new reporting. A normal research pass can gather useful background while still failing to answer the narrow question: is this specific claim supported, contradicted, outdated, or not verifiable from available sources?

Use this skill to turn a claim into structured search queries, collect confirming and contradicting passages from multiple independent sources, assess source independence and recency, then produce a concise verification report with citations and a calibrated verdict.

Quick Start

From this skill directory:

python scripts/verify.py structure --claim "Singapore's GDP grew 4.1% in 2025"

Or use the compatibility shortcut:

python scripts/verify.py --claim "Singapore's GDP grew 4.1% in 2025"

After collecting source passages with a web search tool and web extraction tool, generate a report:

python scripts/verify.py report \
  --claim claim.json \
  --sources sources.json \
  --output verification-report.md

Completion criterion: the report states a verdict, lists every cited source, surfaces contradictions if present, and includes a source-independence note.

When to Use

  • Verify a single factual claim before publishing, sending, or relying on it.
  • Check whether a statistic, event, relationship, quote, or date is supported by sources.
  • Cross-check an agent-written paragraph by verifying its highest-impact claims one by one.
  • Audit a cited claim for source independence and recency.

When NOT to Use

  • Broad topic research or literature review → use a deep research workflow.
  • Full entity background dossiers → use an entity research workflow.
  • Citation database management → use a source tracking workflow.
  • Propaganda, bias, or intent analysis → this skill only verifies factual support.
  • Real-time market, weather, emergency, legal, medical, or regulatory determinations → use authoritative live systems and human review.

Read the full file on GitHub · 243 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 243 lines · 49 tokens per session scan A 1574782672b0

Subscribe to this mod's changes

fact-checker is a skill published in the GitHub repository moonlight-lupin/agent-skills (62 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,765 once invoked, about $0.0002 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.