extract

A command that quickly extracts structured claims from a URL, file, or pasted text without running the full three-stage analysis.

In plain words
What is it for?
Parsing sources, assigning claim IDs and types, rating evidence, estimating credence, recording assumptions and falsifiers, and optionally registering claims in a database.
Why use it?
It provides a faster first pass for turning source material into claims with evidence and confidence details.

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/lhl/realitycheck/extract
Clone the repo
git clone --depth 1 https://github.com/lhl/realitycheck
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 587 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 $0.00012 $0.00587
Opus 5 $0.00006 $0.00293
Sonnet 5 $0.00002 $0.00117
Haiku 4.5 $0.00001 $0.00059

Measured 2d ago against content hash 2a87729e0455, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

integrations/claude/plugin/commands/extract.md · 81 lines

What it actually says

/reality:extract - Claim Extraction

Quick claim extraction from a source without full 3-stage analysis.

Usage

/reality:extract <source>

Arguments

  • source: URL, file path, or pasted text to extract claims from

Process

  1. Parse the source content
  2. Identify extractable claims
  3. For each claim:
    • Assign claim ID: [DOMAIN]-[YYYY]-[NNN]
    • Determine type: [F]/[T]/[H]/[P]/[A]/[C]/[S]/[X]
    • Rate evidence level (E1-E6)
    • Assign credence (0.0-1.0)
    • Note operationalization, assumptions, falsifiers

Registering Claims

After extraction, register claims using the CLI:

# Via shell wrapper
"${CLAUDE_PLUGIN_ROOT}/scripts/run-db.sh" claim add \
  --id "DOMAIN-YYYY-NNN" \
  --text "Claim text" \
  --type "[F]" \
  --domain "TECH" \
  --evidence-level "E3" \
  --credence 0.7 \
  --source-ids "source-id"

# Or directly
uv run python scripts/db.py claim add [OPTIONS]

See /reality:check for fully automated analysis + registration workflow.

Claim Types

Type Symbol Definition
Fact [F] Empirically verified, consensus reality
Theory [T] Coherent explanatory framework with support
Hypothesis [H] Testable proposition, awaiting evidence
Prediction [P] Future-oriented claim with conditions
Assumption [A] Unstated premise underlying other claims
Counterfactual [C] Alternative scenario for comparison
Speculation [S] Untestable or unfalsifiable claim
Contradiction [X] Identified logical inconsistency

Template

Uses methodology/templates/claim-extraction.md

Examples

/reality:extract https://arxiv.org/abs/2301.xxxxx
/reality:extract "AI will automate 50% of jobs by 2030"
  • /reality:check - Full automated analysis workflow
  • /reality:analyze - Full 3-stage analysis
  • /reality:search - Semantic search
  • /reality:stats - Database statistics
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. 2d ago First seen · 81 lines · 12 tokens per session scan A 2a87729e0455

Subscribe to this mod's changes

extract is a command published in the GitHub repository lhl/realitycheck (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 587 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.