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 skills add impactbrussels/AINativeOS --skill frame-the-hypothesisgit clone --depth 1 https://github.com/impactbrussels/AINativeOSWrote 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/skills/impactbrussels/ainativeos/frame-the-hypothesis)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/frame-the-hypothesis"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/frame-the-hypothesis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/frame-the-hypothesis"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/frame-the-hypothesis.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00166 | $0.01033 |
| Opus 5 | $0.00083 | $0.00517 |
| Sonnet 5 | $0.00033 | $0.00207 |
| Haiku 4.5 | $0.00017 | $0.00103 |
Grade A, and why
frame-the-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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame the Hypothesis
AI makes prototyping so cheap it hides the question that actually matters: is the problem real? A working demo proves nothing about demand. This skill turns "I have an AI idea" into "here is the one assumption that decides whether this is real, and the cheapest experiment that could prove me wrong", and it forces the model to attack the idea instead of flattering it.
The method
Sharpen the problem, score the riskiest assumption, write the falsifiable bet, then make the model
attack it. Full anatomy, the uncertainty x fatality rubric, the devil's-advocate protocol, and a worked
example: references/hypothesis-craft.md.
Step 1: Sharpen the problem, not the solution
Reframe in the customer's words: who exactly ([ICP]) fails to get what painful job done ([PROBLEM]),
how do they cope today, and how often does it hurt? Output a one-paragraph problem statement.
Step 2: Name the riskiest assumption
List the beliefs the idea rests on, then flag the one that is both most uncertain and most fatal
if wrong ([RISKIEST_ASSUMPTION]). Usually problem or demand risk, not technical risk.
Step 3: Write the falsifiable hypothesis
State it as: "We believe [X]; we'll know we're wrong if [bar]." Commit to the pass/fail bar
before running anything. If no result could fail it, it's theatre.
Step 4: Run the structured devil's advocate
The model will confirm your idea if you let it (sycophancy).
Instead, make it refute you: "Give five specific reasons this fails, and the cheapest test that would
expose each." Dispatch the devils-advocate agent for a harder pass.
Output
- Problem statement (customer's words) + the assumption stack, riskiest one flagged.
- One falsifiable hypothesis with an explicit pass/fail bar and decision rule.
- The five strongest refutations, and which to test first. Next skill:
map-the-terrainorarchitect-before-code.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 72 lines · 166 tokens per session scan A 8862b0e8c02e
frame-the-hypothesis is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 166 tokens to every session and 1,033 once invoked, about $0.0008 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 skills, from other repositories
nowait-reasoning-optimizer
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens"…
prompt-lookup
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
loom-prompt-engineering
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples.
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.
prompt-engineering
Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.