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 PracticalSwan/agent-skills --skill hypothesis-generationgit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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/practicalswan/agent-skills/hypothesis-generation)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/hypothesis-generation"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/hypothesis-generation/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/practicalswan/agent-skills/hypothesis-generation"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/hypothesis-generation.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 | $0.00058 | $0.03934 |
| Opus 5.5 | $0.00023 | $0.01574 |
| Sonnet 5.5 | $0.00012 | $0.00787 |
| Haiku 4.5 | $0.00006 | $0.00393 |
Grade A, and why
hypothesis-generation 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 8d 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Hypothesis Generation
Turn an observation into a transparent set of candidate explanations and tests. A hypothesis is a proposal to be challenged, not a finding, fact, diagnosis, or recommendation.
Non-negotiable boundaries
Before using unpublished, sensitive, controlled, personal, proprietary, export-controlled, or security-relevant material:
- Confirm authorization and the applicable institutional, funder, publisher, data-use, privacy, and AI policies.
- Keep the material local unless an authorized human explicitly approves a named external destination and data scope.
- Minimize inputs. Do not place sensitive or unpublished data in web searches or external AI systems without authorization.
- Stop at the appropriate human, animal, biosafety, dual-use, data-governance, or regulatory gate.
Never:
- present a hypothesis, mechanism, causal effect, citation, or apparent pattern as established evidence;
- claim novelty because a quick search found nothing;
- infer causation from association, temporal order alone, predictive accuracy, or model output;
- supply patient-specific diagnosis, treatment, dose, prognosis, or other clinical advice;
- provide harmful experimental optimization or operational detail for pathogens, toxins, weapons, evasion, or other misuse;
- bypass IRB/REC, IACUC, IBC, biosafety, dual-use, privacy, legal, or regulatory review;
- fabricate sources, identifiers, search coverage, data, results, approvals, or preregistration;
- automatically score, rank, select, accept, or reject scientific hypotheses.
If a request crosses a safety gate, produce only a high-level risk/oversight note and route it to the qualified local authority. Do not continue with operational detail.
Keep the objects distinct
| Object | Meaning |
|---|---|
| Observation | What was measured, noticed, or reported, with provenance and uncertainty |
| Research question | The answerable question that defines scope |
| Hypothesis | A candidate explanatory or relational proposition |
| Mechanism | The proposed process connecting conditions to an outcome |
| Causal estimand | The precisely defined causal contrast to estimate |
| Prediction | An observable implication derived before checking the target result |
| Alternative explanation | A rival account, including bias or non-causal explanations |
| Null hypothesis | A specified no-effect/no-difference model used by an analysis |
| Negative control | A control expected not to operate through the proposed mechanism |
| Operationalization | How a construct becomes a variable, measurement, intervention, or category |
| Analysis plan | Prespecified transformations, models, contrasts, uncertainty, and decision rules |
| Evidence | Observations or sources that bear on a claim; never the claim itself |
What ships with it
28 files 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.
- assets/evidence_ledger_template.csv 581 B
- assets/falsification_controls_template.json 5.7 KB
- assets/hypothesis_record_template.json 13 KB
- assets/operationalization_template.json 2.2 KB
- assets/prediction_rival_matrix_template.csv 1.6 KB
- assets/preregistration_scaffold_template.md 5.0 KB
- assets/search_boundary_template.json 1.1 KB
- assets/source_ledger.csv 15 KB
- CHANGELOG.md 1.3 KB
- LICENSE.txt 1.0 KB
- references/causal_inference_and_claims.md 7.8 KB
- references/concepts_and_workflow.md 7.2 KB
- references/ethics_safety_and_ai.md 10 KB
- references/experimental_design_patterns.md 9.5 KB
- references/hypothesis_quality_criteria.md 7.8 KB
- references/literature_search_strategies.md 7.9 KB
- references/preregistration_and_open_science.md 7.6 KB
- references/security_validation.md 4.1 KB
- references/source_ledger.md 9.8 KB
- references/tool_reference.md 8.2 KB
- scripts/_common.py 15 KB runs code
- scripts/audit_evidence_ledger.py 12 KB runs code
- scripts/check_falsification_controls.py 16 KB runs code
- scripts/check_operationalization.py 7.9 KB runs code
- scripts/generate_preregistration_scaffold.py 14 KB runs code
- scripts/lint_causal_claims.py 6.6 KB runs code
- scripts/validate_hypothesis_schema.py 38 KB runs code
- scripts/validate_prediction_matrix.py 9.6 KB runs code
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.
- 8d ago First seen · 343 lines · 58 tokens per session scan A 098ab3c89ec0
hypothesis-generation is a skill published in the GitHub repository PracticalSwan/agent-skills (22 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 3,934 once invoked, about $0.0002 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 2026-10-20.
Other skills, from other repositories
mage-antibody-generator
Skill "mage-antibody-generator" from FridrichMethod/awesome-skills, covering copyright notice, copyright (c) 2026 md babu mia, phd, all rights reserved, this code is proprietary and confidential and provenance: authenticated by md babu mia.
figure
Generates complete, runnable visualization code for research figures. Produces matplotlib/seaborn Python scripts for quantitative data and Mermaid diagrams for conceptual relationships, workflows, and taxonomies. Use when the user asks for charts, graphs, visualizations, figures, or diagrams. Produces code only — does…
peer-review
Simulates a full academic journal peer review with EIC decision and 3 independent reviewers (Methodology Expert, Domain Specialist, Devil's Advocate). Scores 1–10, provides major/minor comments, and issues a final verdict: Accept, Minor Revision, Major Revision, or Reject. Use when the user asks for a peer review…
hypothesis
Generates falsifiable, testable research hypotheses from notes, documents, and research content. Use when the user asks to brainstorm hypotheses, generate research questions, identify testable predictions, or discover patterns across their notes. Do NOT use for general Q&A — only when structured hypothesis output is…
validation
Designs detailed experimental protocols to validate research hypotheses. Each protocol includes independent variable, dependent variable, controls, sample size with power analysis, timeline, and expected outcome. Use when the user asks to design experiments, plan a study, propose validation methods, or test a specific…
Scientific Research
Scientific Research delivers source-aware research synthesis with evidence grading, uncertainty tracking, and clear conclusions.