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 poemswe/co-researcher --skill hypothesis-testinggit clone --depth 1 https://github.com/poemswe/co-researcherWrote 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/poemswe/co-researcher/hypothesis-testing)<a href="https://agentmods.dev/skills/poemswe/co-researcher/hypothesis-testing"><img src="https://agentmods.dev/badge/skills/poemswe/co-researcher/hypothesis-testing/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/poemswe/co-researcher/hypothesis-testing"><img src="https://agentmods.dev/badge/skills/poemswe/co-researcher/hypothesis-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01055 |
| Opus 5.5 | $0.00010 | $0.00422 |
| Sonnet 5.5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
hypothesis-testing 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Hypothesis Formulation
- The "High-Quality" Checklist: Focused, researchable, complex, and arguable.
- Directional vs. Non-directional: Specifying effects (H₁: X > Y) vs. differences (H₁: X ≠ Y).
- Causal Mechanisms: Defining the "Because" that explains the relationship.
2. Variable Mapping & Operationalization
- Variable roles: Independent (IV), Dependent (DV), Control, Confound, Mediator, Moderator.
- Scaling: Nominal, Ordinal, Interval, Ratio levels of measurement.
3. Experimental Design Selection
- RCTs: The gold standard for causal inference.
- Quasi-experiments: For cases where random assignment is impossible.
- Observational studies: Longitudinal vs. Cross-sectional designs.
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 Changed · +5 lines 01b326e34e51
- 1mo ago First seen · 79 lines · 25 tokens per session scan A 8475486be98d
hypothesis-testing is a skill published in the GitHub repository poemswe/co-researcher (135 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,055 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
refactor-research-code
Clean research code for public release while preserving reported results. Uses releaseaudit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.
simulate-reviewers
Venue-calibrated peer-review simulation. Use when a researcher says "simulate reviewers", "mock review", "review my paper like a NeurIPS reviewer", "what would Reviewer 2 say", "red-team my paper", "find weaknesses before I submit", "peer review my paper", "strengths and weaknesses / pros and cons of my paper", "what…
verify-results
Check whether reported paper metrics are consistent with outputs from the local code artifact. Use for result reproduction checks, artifact evaluation, reproducibility checklists, code-versus-paper audits, table or claim metric comparisons, and badge-readiness review.
anonymize-paper
Deep anonymization sweep for double-blind paper submissions, plus clean de-anonymization for camera-ready. Use when a researcher says "anonymize my paper", "double-blind check", "blind this submission", "remove author names", "did I leak my identity" — or, after acceptance, "de-anonymize" / "restore authors for…
make-slides
Builds a conference talk deck (Beamer or Marp markdown) from a paper draft - problem-first narrative, one claim per slide, figures reused straight from the paper's LaTeX source, sized to the real slot (12-20 minute full talk vs 5-minute lightning). Use when the user asks to make slides, build a presentation or talk…
prepare-artifacts
Prepares a reproducibility artifact (code/data) for submission and badging. Use when a researcher says "artifact evaluation", "artifact appendix", "reproducibility", "badge", "Artifacts Available/Evaluated/Functional/Reusable", "Results Reproduced/Replicated", "ACM badging", "USENIX/OSDI/SOSP AE", "SIGMOD ARI"…