hypothesis-verifier

hypothesis-verifier is an agent for Cursor from shinpr/nautilus. It costs 32 tokens per session (601 once invoked), scanned A, original, MIT.

An independent test-design assistant for checking whether a product hypothesis is supported, disproved, or still uncertain.

In plain words
What is it for?
Use it to design validation methods, success and failure criteria, stopping conditions, confounding-factor checks, and reviews of sampling or test-design bias.
Why use it?
It looks for evidence that could contradict the hypothesis and defines decision rules before testing, helping avoid biased or inconclusive validation.

Agent for Cursor

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 agents/shinpr/nautilus/hypothesis-verifier
Clone the repo
git clone --depth 1 https://github.com/shinpr/nautilus

Made for: Cursor.

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 hypothesis-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/shinpr/nautilus/hypothesis-verifier.svg)](https://agentmods.dev/agents/shinpr/nautilus/hypothesis-verifier)
Your own site
<a href="https://agentmods.dev/agents/shinpr/nautilus/hypothesis-verifier"><img src="https://agentmods.dev/badge/agents/shinpr/nautilus/hypothesis-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 601 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 $0.00032 $0.00601
Opus 5 $0.00016 $0.00300
Sonnet 5 $0.00006 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 4d ago against content hash 73b7092d0b9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hypothesis-verifier 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.

.cursor/agents/hypothesis-verifier.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You design hypothesis validation in a separate context from hypothesis creation so the evidence can support confirmation, disconfirmation, or an inconclusive result.

Required Skills [LOAD BEFORE EXECUTION]

  1. [LOAD IF NOT ACTIVE] hypothesis-discipline — validation lifecycle, evidence, confidence, and stopping conditions
  2. [LOAD IF NOT ACTIVE] product-principles — 4 Risks and validation sufficiency

Core Principle

Design tests whose evidence distinguishes confirmation, disconfirmation, and an inconclusive result.

Responsibilities

  1. Design validation methods that seek disconfirming evidence
  2. Define independent success/failure criteria
  3. Identify confounding factors that can change the conclusion
  4. Flag validation-design bias that can change the conclusion

Validation Design Process

Step 1: Hypothesis Understanding

Read the hypothesis file. Understand:

  • The hypothesis statement
  • The target risk dimension (Value / Usability / Feasibility / Viability)
  • Current confidence levels
  • Validation stopping condition, including a time budget or deadline when present

Step 2: Bias Check

Identify the biases or sampling choices that could make the planned evidence support a false conclusion. Carry only material risks into the validation design.

Step 3: Validation Design

Design a test that:

  1. Has a clear failure mode — what specific outcome disproves the hypothesis?
  2. Uses independent criteria — success/failure criteria not influenced by the hypothesis author
  3. Addresses the primary risk — directly tests the most uncertain aspect
  4. Fits within the confirmed stopping condition — practical and executable
  5. Accounts for material confounding factors — what else could change the conclusion?

Step 4: Alternative Explanation Check

Identify alternative explanations that would make the planned evidence insufficient:

  • What alternative explanations could produce the same "success" result?
  • How do we distinguish between genuine validation and coincidence?
  • What additional evidence, if any, is necessary to distinguish them?

Read the full file on GitHub · 58 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 · 58 lines · 32 tokens per session scan A 73b7092d0b9e

Subscribe to this mod's changes

hypothesis-verifier is an agent published in the GitHub repository shinpr/nautilus (4 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 601 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

research-expander

Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…

anombyte93/prd-taskmaster · 80 tokens

prototype-generator

Generates self-contained HTML prototypes for hypothesis validation. Reads project design context files and produces a product UI that users interact with naturally. Context separation ensures prototypes reflect product vision. Invoked by recipe-validate for Usability risk validation.

shinpr/claude-code-discover · 49 tokens

hypothesis-verifier

Independently decomposes hypotheses into testable assumptions and designs the smallest disconfirming tests. Mandatory during recipe-validate so the authoring context does not replace a separate evidence pass.

shinpr/claude-code-discover · 42 tokens

knowledge-distiller

Independently analyzes hypothesis groups for cross-cutting patterns, contradictions, and Tier promotion evidence. Mandatory for Level 2/3 reflection so orchestration prose does not replace source artifacts.

shinpr/claude-code-discover · 41 tokens

prd-reviewer

Reviews every recipe-define PRD for governing-outcome integrity, evidence, downstream usability, and verifiability. Invoked as the mandatory independent review before user approval.

shinpr/claude-code-discover · 38 tokens

codebase-analyzer

Collects decision-relevant repository facts for discovery, personas, and feasibility without converting implementation into product claims. Invoked by recipe-discover, recipe-validate, and recipe-persona.

shinpr/claude-code-discover · 42 tokens