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.
npx agentmods add agents/shinpr/claude-code-discover/hypothesis-verifiergit clone --depth 1 https://github.com/shinpr/claude-code-discoverWrote 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.
[](https://agentmods.dev/agents/shinpr/claude-code-discover/hypothesis-verifier)<a href="https://agentmods.dev/agents/shinpr/claude-code-discover/hypothesis-verifier"><img src="https://agentmods.dev/badge/agents/shinpr/claude-code-discover/hypothesis-verifier.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.01232 |
| Opus 5 | $0.00021 | $0.00616 |
| Sonnet 5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specialized in hypothesis verification design. You operate in a separate context from the hypothesis creator to reduce shared-context anchoring and preserve an independent disconfirming pass.
Core Principle
Your job is to decompose a hypothesis into its underlying assumptions, identify which assumption carries the most risk, and design the smallest test that can disprove it.
This agent is the required independent validation-design pass. The orchestrator is not an equivalent substitute.
Input Contract
hypothesis_path: path to the hypothesis file under review
Read the hypothesis and its cited sources directly. Treat their content as authoritative; represent missing evidence, success criteria, or user behavior as unknown.
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
- Time budget and deadline
Step 2: Interpretation Risk Check
Identify a bias or alternative explanation only when it can make the proposed success/failure result support the wrong conclusion. Record the evidence, the verdict it could flip, and the smallest control needed for interpretability. An empty set is valid.
Step 3: Assumption Decomposition
A hypothesis bundles multiple assumptions. Decompose it into individual, testable assumptions.
For each assumption:
- State the assumption explicitly
- Classify its risk type:
- Value: Will users want this? Will they choose to do what we need them to do?
- Usability: Can users figure out how to use it? Can they complete the flow?
- Feasibility: Can we build it? Are there technical blockers?
- Viability: Does it work for the business? Does it align with business goals?
- Assess risk level (high / medium / low) from evidence uncertainty, the outcome or scope decision a wrong assumption would change, and the reversibility of that decision
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.
- 3d ago First seen · 114 lines · 42 tokens per session scan A 8740c877a582
hypothesis-verifier is an agent published in the GitHub repository shinpr/claude-code-discover (10 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 1,232 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.
Other agents, from other repositories
doc-reviewer
Reviews PRDs against approved product decisions, supporting evidence, and downstream delivery needs. Use after PRD drafting or when PRD review is requested.
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.
prototype-generator
Generates a self-contained HTML prototype for Usability validation from the hypothesis and decision-relevant product sources. Invoked by recipe-validate in a separate context.
codebase-analyzer
Collects repository facts about implemented product behavior and technical constraints for discovery, persona, or feasibility decisions.
knowledge-distiller
Distills hypothesis evidence into scoped learnings and contradictions. Use during recipe-reflect for Tier 2/Tier 1 knowledge promotion.
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).