fact-check

fact-check is a command for Claude Code from arielshad/balagan-agent. It costs 6 tokens per session (388 once invoked), scanned A, a copy of fact-check, Apache-2.0.

A claim-checking command that breaks a factual statement into parts and assesses each part against sources and possible counter-evidence.

In plain words
What is it for?
Use it to verify claims, evaluate source quality, add missing context and produce a fact-check report.
Why use it?
It helps identify unsupported, outdated, misleading or only partly true claims instead of relying on an unchecked statement.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to verify claims, evaluate source quality, add missing context and produce a fact-check report.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/arielshad/balagan-agent/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/arielshad/balagan-agent

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/commands/arielshad/balagan-agent/fact-check.svg)](https://agentmods.dev/commands/arielshad/balagan-agent/fact-check)
Your own site
<a href="https://agentmods.dev/commands/arielshad/balagan-agent/fact-check"><img src="https://agentmods.dev/badge/commands/arielshad/balagan-agent/fact-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 388 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 100% copy Near-identical to another mod 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 $0.00006 $0.00388
Opus 5 $0.00003 $0.00194
Sonnet 5 $0.00001 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 8d ago against content hash 8dfbcf06822f, 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 8d 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.

Origin

This is a copy

100% identical to fact-check — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude-agent-sdk-demos/.claude/commands/fact-check.md · 66 lines

What it actually says

Fact-check the following claim: $ARGUMENTS

Verification Process

1. Claim Decomposition

  • Break the claim into verifiable components
  • Identify key facts that need checking
  • Note any ambiguities in the claim

2. Source Search

For each factual component:

  • Find primary sources (official data, academic papers)
  • Find secondary sources (reputable journalism)
  • Look for counter-evidence

3. Verification Assessment

For each component, determine:

  • TRUE: Strong evidence supports this
  • FALSE: Strong evidence contradicts this
  • PARTIALLY TRUE: Some aspects correct, others not
  • UNVERIFIABLE: Cannot confirm with available sources
  • MISLEADING: Technically true but lacks context

4. Context Analysis

  • Is the claim missing important context?
  • Is it outdated information presented as current?
  • Are there caveats being omitted?

5. Source Quality Evaluation

Rate sources on:

  • Authority (expertise of source)
  • Recency (how current)
  • Objectivity (potential bias)
  • Corroboration (multiple sources agree)

Output Format

FACT CHECK REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Claim: [Original claim]
Verdict: [TRUE / FALSE / PARTIALLY TRUE / MISLEADING / UNVERIFIABLE]
Confidence: [HIGH / MEDIUM / LOW]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SUMMARY:
[1-2 sentence summary of finding]

DETAILED ANALYSIS:
[Component-by-component breakdown]

KEY SOURCES:
[List of primary sources used]

IMPORTANT CONTEXT:
[Any context needed to fully understand]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Be rigorous and objective. Acknowledge uncertainty where it exists.

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. 8d ago First seen · 66 lines · 6 tokens per session scan A 8dfbcf06822f

Subscribe to this mod's changes

fact-check is a command published in the GitHub repository arielshad/balagan-agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 6 tokens to every session and 388 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to fact-check, differing in 0 lines, and is treated as a copy.

Related

Other commands, from other repositories

install

Guided setup for a new Cowork workspace. Interviews you (about 5 minutes) and generates a full, pre-configured cowork-os workspace (folders, copy, project instructions, and recurring routines).

yempik-ai/cowork-os · 41 tokens

analyze

Analyze Claude Code transcripts to surface subagent behavior and improvement opportunities.

josix/agent-flow · 0 tokens

knowledge-transfer

Interview a person to capture their operating know-how (tacit knowledge) and write it into the workspace as the company brain: processes, rules with source, glossary, decisions and open questions. For onboarding, a key person leaving, or standardizing a process.

yempik-ai/cowork-os · 52 tokens

linkedin-editor

Run the 8-step LinkedIn editor on any source (an article, a case study, a draft, rough notes) and deliver ready-to-publish, founder-voice LinkedIn posts optimized for reach and leads, not likes.

yempik-ai/cowork-os · 47 tokens

react-router-client-loader

Do this in a clientLoader and use loaderData to render the component. DO NOT create mock data, new interfaces, or mock data loader functions. Instead, assume loaderData has all of the data you need to render the component.

iloveitaly/llm-ide-rules · 0 tokens

pseo-gbp-audit

Use when: kullanıcı "GBP audit", "Google Business Profile kontrol", "placeid eksik mi", "business listing kontrol", "harita listing audit", "google haritalar profili", "GMB audit", "local listing gap" der ya da /pseo-gbp-audit çağırırsa. Also use when: aktif projenin project.config.profiles array'inde "local-service"…

popiliadam/platinum-seo-engine · 231 tokens