fact-check-extract

fact-check-extract is a command for Claude Code from axiomantic/spellbook. It costs 16 tokens per session (1,423 once invoked), scanned A, original, MIT.

A fact-checking step that finds claims in code, documentation, commit messages, and pull requests before judging whether they are true.

In plain words
What is it for?
Use it to prepare a list of claims for verification and identify the evidence needed to assess them.
Why use it?
It prevents important assumptions from being missed and separates collecting claims from checking their accuracy.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to prepare a list of claims for verification and identify the evidence needed to assess them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/fact-check-extract
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/axiomantic/spellbook

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-extract

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/fact-check-extract"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/fact-check-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,423 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 $0.00016 $0.01423
Opus 5 $0.00008 $0.00711
Sonnet 5 $0.00003 $0.00285
Haiku 4.5 $0.00002 $0.00142

Measured 5d ago against content hash b2c201be8d8c, 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-extract 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 5d 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/fact-check-extract.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fact-Check: Claim Extraction and Triage (Phases 2-3)

Invariant Principles

  1. Extract before judging -- collect all claims before assessing truth
  2. Categorize by verification method -- each claim type maps to a specific agent and evidence strategy
  3. Implicit claims count -- naming conventions and code structure assert claims as strongly as explicit comments

Phase 2: Claim Extraction

Sources:

Source Patterns
Comments //, #, /* */, """, ''', <!-- -->, --
Docstrings Function/class/module documentation
Markdown README, CHANGELOG, docs/*.md
Commits git log --format=%B for branch commits
PR descriptions Via gh pr view
Naming validateX, safeX, isX, ensureX

If a source is inaccessible (no git history, no PR): skip and log ⚠ [Source] unavailable -- skipped. If no claims found across all sources: report "No verifiable claims found" and halt.

CoVe Self-Interrogation on Extracted Claims

After extracting claims from all sources and before triage, apply CoVe self-interrogation (per skills/shared-references/cove-protocol.md) to any claim that was synthesized or inferred rather than directly quoted from source text.

Synthesized claims include:

  • Claims where the extractor paraphrased or summarized source text
  • Implicit claims inferred from naming conventions (from Naming Convention Scan below)
  • Claims combining information from multiple sources

For each synthesized claim, run the three-step protocol:

  1. Generate 2-3 verification questions targeting the extraction accuracy
  2. Answer each using the source text (re-read if necessary)
  3. Revise the claim if any answer contradicts the extraction

Read the full file on GitHub · 126 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. 5d ago First seen · 126 lines · 16 tokens per session scan A b2c201be8d8c

Subscribe to this mod's changes

fact-check-extract is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,423 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 2026-09-03.