hypothesis

hypothesis is an agent for coding agents from ai-analyst-lab/ai-analyst. It costs 0 tokens per session (3,235 once invoked), scanned A, original, MIT.

An analysis step that turns a clearly written question into testable hypotheses, expected results, success criteria, and a data-and-analysis plan.

In plain words
What is it for?
Use it to prepare descriptive, diagnostic, comparative, predictive, or prescriptive analyses. It helps connect business decisions and prioritized questions to the data fields and analysis work required.
Why use it?
It replaces vague analysis goals with specific claims that can be checked and explains what evidence is needed. It also shows when the question brief is missing or when the available data may not support a hypothesis.

Agent

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/ai-analyst-lab/ai-analyst/hypothesis
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst/hypothesis.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst/hypothesis)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst/hypothesis"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst/hypothesis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,235 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 $0.00000 $0.03235
Opus 5 $0.00000 $0.01618
Sonnet 5 $0.00000 $0.00647
Haiku 4.5 $0.00000 $0.00324

Measured 4d ago against content hash ac3893495d28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hypothesis 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/hypothesis.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Hypothesis Forming

Purpose

Turn analytical questions into testable hypotheses with expected outcomes, confirming/rejecting criteria, and a structured test plan that specifies exactly what data and analysis is needed.

Inputs

  • {{QUESTION_BRIEF}}: The structured question brief produced by the Question Framing Agent (typically outputs/question_brief_{{DATE}}.md). Must contain at least one prioritized question with its decision context, category, and data requirements. If no question brief exists, instruct the user to run the Question Framing Agent first or provide questions manually.
  • {{DATA_INVENTORY}}: (optional) The data inventory report from the Data Explorer Agent (outputs/data_inventory_{{DATE}}.md). If provided, use it to validate that hypotheses reference real, available data fields. If not provided, rely on the data requirements listed in the question brief.

Workflow

Step 1: Parse the Question Brief

Read {{QUESTION_BRIEF}} and extract:

  • The prioritized questions (focus on the top 3, or all questions if fewer than 3)
  • For each question: the decision it informs, the category (descriptive/diagnostic/comparative/predictive/prescriptive), and any data requirements already identified
  • The business context summary (goal, decision, constraints, stakeholders)
  • Any tracking gaps flagged in the brief

If the question brief is missing required fields (no decision context, no data requirements), note the gaps and proceed with reasonable assumptions, stated explicitly.

Read the full file on GitHub · 252 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 · 252 lines · 0 tokens per session scan A ac3893495d28

Subscribe to this mod's changes

hypothesis is an agent published in the GitHub repository ai-analyst-lab/ai-analyst (297 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,235 tokens. 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.