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 airas-org/airas --skill hypothesize-and-designgit clone --depth 1 https://github.com/airas-org/airasWrote 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/airas-org/airas/hypothesize-and-design)<a href="https://agentmods.dev/skills/airas-org/airas/hypothesize-and-design"><img src="https://agentmods.dev/badge/skills/airas-org/airas/hypothesize-and-design/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/airas-org/airas/hypothesize-and-design"><img src="https://agentmods.dev/badge/skills/airas-org/airas/hypothesize-and-design.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 | $0.00051 | $0.00408 |
| Opus 5 | $0.00026 | $0.00204 |
| Sonnet 5 | $0.00010 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
hypothesize-and-design 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.
What it actually says
Hypothesize & design
Needs a research_study_list (prior work to build on).
- Author the hypothesis via
get_generation_prompt("hypothesis", ...)with the study list. Write the prose in Japanese;primary_metric/supporting_metricsstay English identifiers (parsed downstream). - Fix the compute target first: ask the user if it is not known,
record GPU and
arch(x86_64/aarch64) — the design and later the dependency lockfile depend on it. - Author the design via
get_generation_prompt("experimental_design", ...).retrieve_models/retrieve_datasetslist curated candidates (no key needed); pass those rather than the prompt's built-in language-model defaults for any other field. - Leave run ids and metrics settled. Downstream tooling addresses
every result as
<run_id>.<metric.path>(e.g.proposed.accuracy), so a design that leaves run naming open is not finished. State the expected magnitude of the effect as an interval (a range, not a point) and what outcome would refute the hypothesis — a hypothesis without a refutation condition is not testable.
Output: hypothesis + experimental design, written to
.research/research_history.json in the experiment repository when one
exists (state belongs in the clone, not the conversation). This is the
working draft: preregister-paper freezes it into the canonical
.research/record.json, after which revision is append-only.
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 · 34 lines · 51 tokens per session scan A d760d2915418
hypothesize-and-design is a skill published in the GitHub repository airas-org/airas (33 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 408 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
research-proof
Turn vague research ideas, math-heavy claims, AI-lab style agent loops, benchmark claims, causal claims, prototype-readiness claims, design research, prompt-injection-sensitive evidence reviews, and medical-research style questions into falsifiable proof programs with fixed Claim/Verifier/Current…
proof-checker
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
auto-paper-improvement-loop
An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-write
A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.