hypothesis

hypothesis is a command for coding agents from Aznatkoiny/zAI-Skills. It costs 8 tokens per session (630 once invoked), scanned A, original, MIT.

A command for turning a question into several specific, testable explanations. It also defines what evidence would support or disprove each explanation and what analysis is needed.

In plain words
What is it for?
Use it to frame market research, product investigations, strategy questions, or debugging work around claims that can be checked.
Why use it?
It prevents unfocused research and makes it harder to mistake evidence that merely confirms an early guess for proof.

Command

Part of the consulting-toolkit plugin — 1 skill, 17 commands, 5 agents shipped together

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/aznatkoiny/zai-skills/hypothesis
Clone the repo
git clone --depth 1 https://github.com/Aznatkoiny/zAI-Skills

Or install consulting-toolkit, the plugin that ships this one along with the rest of its 1 skill, 17 commands, 5 agents.

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/commands/aznatkoiny/zai-skills/hypothesis.svg)](https://agentmods.dev/commands/aznatkoiny/zai-skills/hypothesis)
Your own site
<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/hypothesis"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/hypothesis.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 630 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 $0.00008 $0.00630
Opus 5 $0.00004 $0.00315
Sonnet 5 $0.00002 $0.00126
Haiku 4.5 $0.00001 $0.00063

Measured 5d ago against content hash 56c4a750f82e, 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 5d 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.

consulting-toolkit/commands/hypothesis.md · 51 lines

What it actually says

You are a senior consultant at a top-tier strategy firm. Hypothesis-driven problem solving is the core methodology: start with the answer, then design the work to prove or disprove it. This approach prevents "boiling the ocean" — the team only does analysis that moves the answer forward.

For this question: $ARGUMENTS

  1. GENERATE 3-5 HYPOTHESES — each must be:

    • A specific, falsifiable claim (not a vague direction)
    • Mutually exclusive where possible (testing one should narrow the field)
    • Grounded in some initial logic or pattern, not random guesses
    • Bad: "The market might be attractive"
    • Good: "The European cold chain market will exceed €50B by 2028, driven by pharmaceutical logistics demand growing at >8% CAGR, making it attractive for entry"
  2. FOR EACH HYPOTHESIS, DEFINE:

    • The claim: State it as a complete, testable sentence
    • Supporting evidence: What data or findings would confirm it?
    • Refuting evidence: What data or findings would kill it? (This is the more important question — confirmation bias is the enemy)
    • Key analysis: The specific work required to test it (e.g., "bottom-up market model using pharmacy distribution data" not "market research")
    • Data sources: Where the evidence would come from
    • Kill criteria: At what threshold do you abandon this hypothesis?
  3. PRIORITIZE — recommend which hypothesis to test first. The right answer is usually the one that is:

    • Most likely to be true (highest prior probability)
    • Cheapest/fastest to test
    • Most decisive (if confirmed, it most changes the recommendation) The intersection of these three is your starting point.
  4. DESIGN THE TEST SEQUENCE — if H1 is confirmed, what do you test next? If refuted? Map the decision tree so the team knows the full testing roadmap, not just step one.

<output_format> For each hypothesis, present as:

H[n]: [Complete hypothesis statement]

  • If true: [What evidence you'd expect to see]
  • If false: [What evidence would refute it]
  • Test via: [Specific analysis or data gathering]
  • Data source: [Where to find it]
  • Kill criteria: [Threshold for abandoning]
  • Priority: [High/Medium/Low] — [one-line rationale]

Then:

  • Recommended test sequence: H[x] first → if confirmed, H[y] → ...
  • Rationale: Why this sequence is most efficient </output_format>
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. 5d ago First seen · 51 lines · 8 tokens per session scan A 56c4a750f82e

Subscribe to this mod's changes

hypothesis is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 630 once invoked, about $0.0000 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 commands, from other repositories

composite-actions

Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.

nitinjain999/platform-skills · 51 tokens

github-actions

Design, review, secure, and debug GitHub Actions workflows — reusable workflows, OIDC federation, SHA pinning, token scoping, promotion orchestration, and CI failure diagnosis.

nitinjain999/platform-skills · 40 tokens

datadog

Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.

nitinjain999/platform-skills · 57 tokens

fluxcd

FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.

nitinjain999/platform-skills · 71 tokens

linkerd

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

nitinjain999/platform-skills · 30 tokens

terraform

Runs through the full Terraform validation pipeline — fmt, validate, tflint, security scan — and reviews a module or plan for blast radius, IAM risk, and state impact.

nitinjain999/platform-skills · 38 tokens