fact-check

fact-check is a command for Claude Code from alberduris/skills. It costs 22 tokens per session (379 once invoked), scanned A, original, MIT.

A command that checks a generated newspaper report against the actual code, git history, and data, then corrects factual errors in the report.

In plain words
What is it for?
Fact-checking an HTML report, verifying its measurable and structural claims, and updating incorrect details in place.
Why use it?
It reduces mistakes in claims about files, functions, numbers, dependencies, behavior, and change history.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the newspaper-explainer plugin — 1 skill, 8 commands shipped together

Good fit Fact-checking an HTML report, verifying its measurable and structural claims, and updating incorrect details in place.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alberduris/skills/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/alberduris/skills

Made for: Claude Code.

Or install newspaper-explainer, the plugin that ships this one along with the rest of its 1 skill, 8 commands.

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/alberduris/skills/fact-check/github.svg)](https://agentmods.dev/commands/alberduris/skills/fact-check)
Your own site
<a href="https://agentmods.dev/commands/alberduris/skills/fact-check"><img src="https://agentmods.dev/badge/commands/alberduris/skills/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/commands/alberduris/skills/fact-check"><img src="https://agentmods.dev/badge/commands/alberduris/skills/fact-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 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 $0.00022 $0.00379
Opus 5 $0.00011 $0.00189
Sonnet 5 $0.00004 $0.00076
Haiku 4.5 $0.00002 $0.00038

Measured 9d ago against content hash 85f9b826e38a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/newspaper-explainer/skills/newspaper-explainer/commands/fact-check.md · 13 lines

What it actually says

Load the newspaper-explainer skill. Read ./templates/broadsheet.html and ./references/css-patterns.md to match the existing page's styling when inserting the verification summary. Then verify the factual accuracy of the target file.

The target is $1 (explicit path to an HTML file; if omitted, verify the most recently modified file in ~/.agent/newspapers/). This is a FACT-CHECKER, not a re-review — it does not second-guess analysis, opinions, or editorial judgments. It verifies that data presented matches reality, corrects what does not, and leaves everything else alone.

Extract every verifiable claim from the file: a) quantitative figures (line counts, file counts, function counts, percentages), b) names (functions, types, modules, file paths referenced), c) behavioral descriptions (what code does, how things work, before/after comparisons), d) structural claims (architecture, dependencies, import chains), e) temporal claims (git history, commit attributions, timeline). Skip subjective analysis. For each claim, go to the source — re-read files, re-run git commands, compare output against the newspaper's assertions. Classify each as CONFIRMED, CORRECTED (note what was wrong and the correct value), or UNVERIFIABLE.

Correct inaccuracies IN PLACE using surgical text replacements — fix numbers, names, paths, behavior descriptions, before/after swaps. Preserve layout, CSS, and structure. After corrections, insert a compact verification summary section at the bottom of the page matching the existing styling: total claims checked, confirmed count, corrections made with brief descriptions, unverifiable claims flagged. Tell the user what was checked, what was corrected, and open the file in the browser.

$@

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. 9d ago First seen · 13 lines · 22 tokens per session scan A 85f9b826e38a

Subscribe to this mod's changes

fact-check is a command published in the GitHub repository alberduris/skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 379 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 2026-08-30.