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 skills/impactbrussels/ainativeos/hypothesis-miningnpx skills add impactbrussels/AINativeOS --skill hypothesis-mininggit 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/hypothesis-mining)<a href="https://agentmods.dev/skills/impactbrussels/ainativeos/hypothesis-mining"><img src="https://agentmods.dev/badge/skills/impactbrussels/ainativeos/hypothesis-mining.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 | $0.00152 | $0.01310 |
| Opus 5 | $0.00076 | $0.00655 |
| Sonnet 5 | $0.00030 | $0.00262 |
| Haiku 4.5 | $0.00015 | $0.00131 |
Grade A, and why
hypothesis-mining 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Mining
You have done the research and now you are drowning in it: transcripts, support tickets, keyword volumes, a stack of papers, competitor one-star reviews. The temptation is to test the assumption that is easiest to check or most pleasant to confirm. That is how founders spend three months proving the technology runs while the real killer, that nobody will pay, goes untested. Mine the input into a ranked stack of falsifiable bets and test the one that is most uncertain and most fatal first.
The method
Mine, classify by risk, score by uncertainty times fatality. Full framework: Handbook
Chapter 02. Deep method, scoring grid, and a worked
example: references/hypothesis-mining-method.md.
Step 1: Mine every source for raw beliefs
Sweep all the input and pull out the implied beliefs. Different sources surface different risks, so mine widely before you rank.
| Source | What it reveals best |
|---|---|
| Interview transcripts | Problem and demand risk; the workaround that proves pain |
| Support logs / forum threads | Live pain in the customer's own words |
| Search / keyword volume | Whether anyone is already looking for this |
| Papers / patents | Feasibility risk; what is known to be hard |
| Competitor reviews (1-star) | The unmet job a rival left open |
Step 2: Write each as a falsifiable hypothesis
State every belief as: "We believe [X]; we'll know we're wrong if [bar]." Set the pass/fail
number before any test. If no result could fail it, it is not a hypothesis, it is a wish. Forbid
solution-shaped claims ("users want our dashboard"); restate as a problem belief.
Step 3: Classify the risk
Sort each hypothesis into one bucket, because you test them differently.
| Risk type | The question it answers |
|---|---|
| Problem | Is the pain real and felt? |
| Demand | Will they move and pay to fix it? |
| Solution | Does our approach actually solve it? |
| Feasibility | Can we build it, legally and technically? |
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.
- 3d ago First seen · 95 lines · 0 tokens per session scan A 73bc0dbb14fc
hypothesis-mining is a skill published in the GitHub repository impactbrussels/AINativeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 152 tokens to every session and 1,310 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
agent-session-monitor
Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
architecture-reviewer
Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before…
ralph-specum-requirements
This skill should be used only when the user explicitly asks to use $ralph-specum-requirements, or explicitly asks Ralph Specum in Codex to run the requirements phase.