A command for a full Reality Check analysis workflow: fetching a source, examining it, extracting claims, registering results, and validating them.

Analyzing a URL or continuing an existing analysis, with optional domain hints, a quicker mode, and registration controls.

It provides a defined process for recording evidence levels and confidence instead of producing an unstructured source summary.

check — Command by lhl

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/check

Clone the repo

git clone --depth 1 https://github.com/lhl/realitycheck

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 1,136 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.01136
Opus 5	$0.00008	$0.00568
Sonnet 5	$0.00003	$0.00227
Haiku 4.5	$0.00002	$0.00114

Measured yesterday against content hash 9aa761e84b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/check.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reality:check - Full Analysis Workflow

The flagship Reality Check command for rigorous source analysis.

Core Methodology: See methodology/workflows/check-core.md for the complete 3-stage analysis methodology, evidence hierarchy, claim types, and extraction format.

Before starting, read methodology/workflows/check-core.md and follow its Output Contract. In particular: the analysis markdown must include claim tables with evidence levels and credence (do not omit).

IMPORTANT: Always write to the DATA repository (pointed to by REALITYCHECK_DATA), never to the framework repository. If you see scripts/, tests/, integrations/ - you're in the wrong repo.

Usage

/reality:check <url>
/reality:check <url> --domain TECH --quick
/reality:check <source-id> --continue
/reality:check --continue

Arguments

url: URL of the source to analyze
--domain: Primary domain hint (TECH/LABOR/ECON/GOV/SOC/RESOURCE/TRANS/GEO/INST/RISK/META)
--quick: Skip Stage 3 (dialectical analysis) for faster processing
--no-register: Analyze without registering to database
--continue: Continue/iterate on an existing analysis instead of starting fresh

Workflow Steps

Fetch - Use WebFetch to retrieve source content
Metadata - Extract title, author, date, type, generate source-id
Analysis - Perform 3-stage analysis (see methodology)
Neutral Analyst Prose Pass - Clean up analyst-authored prose without changing source content, quotes, claim IDs, evidence levels, or credences
Extract - Format claims as YAML (see methodology)
Register - Add source and claims to database
Audit Log - Append in-document Analysis Log + register analysis_logs row
Validate - Run integrity checks
README - Update data project analysis index
Report - Generate summary

The neutral prose pass applies to the analysis voice, not the content being analyzed. Do not remove direct quotes, source wording, titles, quoted slogans, or examples in persuasion/rhetoric analysis; label those as source language instead of adopting them as the analyst's framing.

Read the full file on GitHub · 121 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.

yesterday First seen · 121 lines · 16 tokens per session scan A 9aa761e84b01

Subscribe to this mod's changes

check is a command published in the GitHub repository lhl/realitycheck (41 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,136 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.

Productivity Research agent analysis

check

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/reality:check - Full Analysis Workflow

Usage

Arguments

Workflow Steps

What this file has done since we first saw it

Other commands, from other repositories

MIGRATE_DESIGN

awesome-chatgpt

agentlas-cloud

commit

webapp-testing

create-issue