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/openscientist-io/openscientist/hypothesis-generationnpx skills add openscientist-io/openscientist --skill hypothesis-generationgit clone --depth 1 https://github.com/openscientist-io/openscientistWrote 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/openscientist-io/openscientist/hypothesis-generation)<a href="https://agentmods.dev/skills/openscientist-io/openscientist/hypothesis-generation"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/hypothesis-generation.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 5.1 | $0.00013 | $0.00990 |
| Opus 5 | $0.00006 | $0.00495 |
| Sonnet 5 | $0.00003 | $0.00198 |
| Haiku 4.5 | $0.00001 | $0.00099 |
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 6d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hypothesis Generation
When to Use This Skill
- After identifying an interesting pattern in the data
- When a previous hypothesis was rejected (need to generate alternatives)
- At the start of investigation (bootstrap from literature)
- When you're stuck and need fresh ideas
The Process
1. Review Current Knowledge
What patterns have been observed?
- Check the knowledge graph summary
- What group differences exist?
- What correlations are surprising?
- What contradicts expectations?
What has been tested already?
- Which hypotheses were supported?
- Which were rejected? (Don't repeat these!)
- What did negative results tell us?
What does literature say?
- Search PubMed for relevant papers
- Extract known mechanisms
- Identify knowledge gaps
2. Formulate Specific, Testable Hypotheses
Good hypotheses have this structure: "X causes Y via mechanism Z"
Examples:
- ✅ Good: "Hypothermia increases nucleotide salvage flux by upregulating APRT enzyme activity"
- ❌ Too vague: "Metabolism changes in hypothermia"
- ❌ Not testable: "The brain adapts to cold"
Requirements:
- Must be testable with available data
- Must be falsifiable (can prove it wrong)
- Should suggest a specific analysis
- Should have mechanistic basis (not just correlation)
3. Prioritize Hypotheses
Score each hypothesis on:
Impact (1-5): How central to the research question?
- 5 = Directly explains the core phenotype
- 3 = Fills in a mechanistic detail
- 1 = Minor tangential observation
Feasibility (1-5): Can we test it with current data?
- 5 = Have all required variables
- 3 = Can construct proxy measure
- 1 = Missing critical data
Novelty (1-5): Is this a new insight?
- 5 = No one has asked this before
- 3 = Refinement of known mechanism
- 1 = Well-studied question
Coherence (1-5): Fits with existing findings?
- 5 = Explains contradictions or connects findings
- 3 = Extends current model
- 1 = Orthogonal to other findings
Total Priority Score = Impact × 0.4 + Feasibility × 0.3 + Novelty × 0.2 + Coherence × 0.1
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.
- 6d ago First seen · 134 lines · 13 tokens per session scan A 3e5f706d9847
hypothesis-generation is a skill published in the GitHub repository openscientist-io/openscientist (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 990 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via deriveoutlineprompt (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → render each panel with paneltask (loading figure-style), one at a time or…
paper-narrative
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. paperbriefprompt(abstract, captions) hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and…
tao-run-deft-cr-its-mining
Run the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. Use when the user asks for a DEFT CR ITS mining workflow, traffic-camera Cosmos Reason improvement loop, collision-identification workflow with data mining, or…
tao-run-deft-object-detection
Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool, ODVG dataset staging, and retraining — repeated for a fixed number of…
sciverse-paper-search
Use this skill for scientific literature search, evidence retrieval, paper metadata screening, and cited research synthesis with Sciverse. This LazyLLM-adapted version supports SciverseSearch search, metasearch, metacatalog, and getcontent only; it does not assume full Sciverse MCP resource or attachment APIs are…
paper-search
Primary skill for searching, retrieving, and reading academic papers from arXiv.