factcheck

factcheck is a command for coding agents from sergei-aronsen/claude-code-toolkit. It costs 0 tokens per session (741 once invoked), scanned A, original, MIT.

A command that checks one factual claim against current web sources and returns whether it is verified, disputed, or cannot be verified. It includes supporting citations.

In plain words
What is it for?
Use it to verify a single version-sensitive statement, such as whether a database release happened or whether a framework supports a particular feature.
Why use it?
It helps catch outdated or incorrect claims in plans, specifications, comments, and AI-generated text before you rely on them.

Command

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.

agentmods
npx agentmods add commands/sergei-aronsen/claude-code-toolkit/factcheck
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

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 factcheck

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/factcheck.svg)](https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/factcheck)
Your own site
<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/factcheck"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/factcheck.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 741 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00741
Opus 5 $0.00000 $0.00370
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash c3d35e5b0ac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factcheck 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 4d 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.

commands/factcheck.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/factcheck — Verify a Specific Claim with Sources

Purpose

Verify a single factual claim against current web sources. Returns a verdict (VERIFIED, DISPUTED, UNVERIFIABLE) with supporting citations.

Built on the same comet-bridge MCP as /research and /lookup — uses your Perplexity Pro subscription, no API tokens spent.


Usage

/factcheck <claim>

Examples:

  • /factcheck Postgres 18 was released in 2026
  • /factcheck React 19 deprecates the legacy Context API
  • /factcheck Stripe Treasury accepts EUR deposits in May 2026
  • /factcheck Bun supports Node-native HTTP/2 in production

When to Use

  • Reviewing a plan / spec / comment that contains version-sensitive claims
  • Auditing AI-generated text for hallucinated facts
  • Pre-flight check before relying on a "fact" in code or docs

Use /research instead when:

  • The question is open-ended ("what's new in X?")

Use /lookup instead when:

  • You want an answer, not a verdict on a specific assertion

Pre-flight Checks

Same as /research. Falls back to WebSearch + reasoning if comet-bridge is unavailable, but the verdict will be lower-confidence.


Process

  1. Call mcp__comet-bridge__comet_connect.

  2. Call mcp__comet-bridge__comet_ask with a structured verification prompt:

    Fact-check this claim and return a verdict.
    
    Claim: "<user claim>"
    
    Required output:
    1. Verdict: VERIFIED | DISPUTED | UNVERIFIABLE
    2. One-sentence justification
    3. 2-4 supporting sources with titles and URLs
    4. If DISPUTED: what the actual current state is
    

    With mode: search, timeout: 60000.

  3. Parse the structured response. If the model didn't follow the format, fall back to extracting verdict heuristically (look for keywords: "true / false / partially / no evidence").


Output Format

**Claim:** <user claim>

**Verdict:** ✅ VERIFIED  |  ❌ DISPUTED  |  ❓ UNVERIFIABLE

**Justification:** <one-line explanation>

<if DISPUTED>
**Actual state:** <correct version of the fact>
</if>

**Sources:**
- [<title>](<url>)
- [<title>](<url>)

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 0 tokens per session scan A c3d35e5b0ac4

Subscribe to this mod's changes

factcheck is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 741 tokens. 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 2026-08-31.