A command that examines a source in three stages: it summarizes the claims, tests their evidence and logic, and compares them with counterarguments and alternatives. It is part of the Reality Check methodology.

Use it to assess a web page or saved source, extract its assumptions and predictions, look for evidence against it, and produce an overall critical analysis.

It helps separate what a source says from how well its claims are supported. This reduces the risk of accepting unsupported, inconsistent, or unfalsifiable arguments.

analyze — 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/analyze

Clone the repo

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

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 691 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	$0.00015	$0.00691
Opus 5	$0.00008	$0.00345
Sonnet 5	$0.00003	$0.00138
Haiku 4.5	$0.00002	$0.00069

Measured 2d ago against content hash a8fd924afb54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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/analyze.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reality:analyze - Source Analysis

Perform a full 3-stage analysis of a source following the Reality Check methodology.

Usage

/reality:analyze <url_or_source_id>

Arguments

url_or_source_id: URL to analyze or existing source ID to re-analyze

Methodology

Stage 1: Descriptive Analysis

Summarize the source neutrally
Extract key claims, predictions, and assumptions
Identify theoretical lineage
Note scope and domain
Define key terms with operational proxies

Stage 2: Evaluative Analysis

Assess internal coherence and logical consistency
Evaluate evidence quality and empirical grounding
Identify unstated assumptions and dependencies
Rate credence levels using the Evidence Hierarchy
Flag unfalsifiable claims
Search for disconfirming evidence
Check for internal tensions/self-contradictions
Note persuasion techniques used

Stage 3: Dialectical Analysis

Steelman the strongest version of the argument
Identify strongest counterarguments and counterfactuals
Consider base rates and historical analogs
Map relationships to other theories
Map interventions: what would change these claims?
Synthesize: where does this fit in the broader landscape?

Neutral Analyst Prose Pass

Apply this pass to the analyst's prose, not to source text, direct quotes, titles, quoted slogans, or persuasion/rhetoric examples.
Remove rhetorical setup, marketing language, vague intensifiers, hedge stacks, and conclusion recaps from analyst prose.
Preserve source wording when it is evidence for rhetoric, framing, or persuasion; label it as source language instead of adopting it as the analyst's voice.

Output

The analysis will:

Guide you through 3-stage methodology
Help extract and classify claims with unique IDs
Generate an analysis document in analysis/sources/

Database Registration

After analysis, register sources and claims using the CLI:

# Register source
"${CLAUDE_PLUGIN_ROOT}/scripts/run-db.sh" source add \
  --id "author-year-slug" \
  --title "Title" \
  --type "PAPER" \
  --author "Author Name" \
  --year 2026 \
  --url "https://..."

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

Read the full file on GitHub · 105 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.

2d ago First seen · 105 lines · 15 tokens per session scan A a8fd924afb54

Subscribe to this mod's changes

analyze is a command published in the GitHub repository lhl/realitycheck (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 691 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.

Research agent analysis

analyze