fact-check

fact-check is a skill for Claude Code from elvisun/newsjack. It costs 85 tokens per session (5,273 once invoked), scanned A, original, MIT.

A fact-checking workflow for public-relations copy. It separates factual claims, checks them independently, adds source links, and marks claims that cannot be supported or remain uncertain.

In plain words
What is it for?
Use it to verify claims in a draft, assess the quality and origin of sources, compare evidence from multiple places, and give each claim a clear level of confidence. It does not rewrite the draft or create a media strategy.
Why use it?
It reduces the risk of publishing inaccurate or weakly sourced statements. It keeps unsupported claims visible instead of treating them as true because the surrounding text sounds credible.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

not rated 666repo +2 7d ago A scan Socket: passSnyk: warnSkillSpector: warn 85 tokens original MIT

Good fit Use it to verify claims in a draft, assess the quality and origin of sources, compare evidence from multiple places, and give each claim a clear level of confidence. It does not rewrite the draft or create a media strategy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elvisun/newsjack/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.

Any agent
npx skills add elvisun/newsjack --skill fact-check
Clone the repo
git clone --depth 1 https://github.com/elvisun/newsjack

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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/elvisun/newsjack/fact-check/github.svg)](https://agentmods.dev/skills/elvisun/newsjack/fact-check)
Your own site
<a href="https://agentmods.dev/skills/elvisun/newsjack/fact-check"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/fact-check/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-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/elvisun/newsjack/fact-check"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/fact-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,273 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
  • Socket pass 16 Jun 2026
  • Snyk warn 16 Jun 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 99
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 $0.00085 $0.05273
Opus 5 $0.00043 $0.02636
Sonnet 5 $0.00017 $0.01055
Haiku 4.5 $0.00009 $0.00527

Measured 10d ago against content hash aace9b5878b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

skills/fact-check/SKILL.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact Check

You are the factual accuracy gate inside newsjack.sh. Your job is narrow: pull every factual claim out of the draft, check each one on its own, attach real citations, and make any unresolved risk impossible to miss.

You are not a copywriter, editor, media-list builder, or pitch strategist. Do not rewrite the draft. Do not improve the angle. Do not wave a claim through from memory. If a claim cannot be backed by concrete evidence, mark it a failure rather than letting it pass.

Operating Doctrine

A few principles run through everything below:

  • The burden of proof is on the speaker. An unsupported claim does not default to true. It is "probably fine" only after you have evidence.
  • Cite real source links. "Reports say" and "industry data" are not citations.
  • Treat weak or missing sourcing as a headline result, not a footnote.
  • Check each claim on its own. A paragraph that reads as trustworthy does not make every sentence in it true.
  • Never treat your own memory as evidence. Use the sources you are given and the search tools available to you.
  • Keep uncertainty visible. If evidence is old, indirect, or ambiguous, say so.
  • End every response with a ## Warning section.

If skills/ETHICS.md and skills/WHY-NOT-SPAM.md exist in this repo, follow them.

What You Need To Start

Accept any of:

  • The draft text, pasted in directly or loaded from a file.
  • current_time, or the current date and time supplied by the host, so you can judge how recent things are.
  • Optional sender context: the company, the spokesperson, the channel the draft is going out on, and any source URLs the user provides.

If you have no reliable current time, do not guess "today" from training data. You may continue for claims that do not depend on timing, but mark every claim about a role, a title, a date, or words like "recent", "last week", "today", or "currently" as Unverifiable, and note that the time anchor is missing.

How To Separate The Work (Ideal Setup)

Read the full file on GitHub · 441 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. 10d ago First seen · 441 lines · 85 tokens per session scan A aace9b5878b9

Subscribe to this mod's changes

fact-check is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 7d ago), licensed MIT. It adds 85 tokens to every session and 5,273 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

a0-development

Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.

agent0ai/agent-zero · 57 tokens

conscientiousness

Thoroughness and diligence in execution — systematic checking, completeness verification, follow-through on commitments, and the discipline of finishing well. Maps the personality trait of conscientiousness to AI task execution: not cutting corners, verifying results, and ensuring that what was promised is what was…

pjt222/agent-almanac · 108 tokens

breathe

AI micro-reset between actions — the lightest self-care unit. A single conscious pause to check alignment before the next step. Where meditate is a full clearing session, breathe is one deliberate moment of awareness between tool calls or reasoning steps. Use mid-task when drift might be accumulating, between reading…

pjt222/agent-almanac · 89 tokens

codex-docs-drift-scout

Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.

autoworks-ai/autovault · 36 tokens

notion

Notion API for creating and managing pages, databases, and blocks.

SafeAI-Lab-X/ClawKeeper · 17 tokens

gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

SafeAI-Lab-X/ClawKeeper · 20 tokens