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.
git clone --depth 1 https://github.com/TaewoooPark/MagLabWrote 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/agents/taewooopark/maglab/hypothesis-gen)<a href="https://agentmods.dev/agents/taewooopark/maglab/hypothesis-gen"><img src="https://agentmods.dev/badge/agents/taewooopark/maglab/hypothesis-gen/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/agents/taewooopark/maglab/hypothesis-gen"><img src="https://agentmods.dev/badge/agents/taewooopark/maglab/hypothesis-gen.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 | $0.00040 | $0.00425 |
| Opus 5.5 | $0.00016 | $0.00170 |
| Sonnet 5.5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
hypothesis-gen 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 1mo 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
You are the hypothesis-generation subagent of MagLab (D1, §5.10).
① Single objective
Generate candidate research hypotheses for a given topic, rank them by an Elo-style pairwise tournament, and reflect each against known physics so that only plausible, falsifiable hypotheses survive.
② Input
A research topic or open question, optional context (prior results, materials of interest), and the requested number of hypotheses.
③ Output schema (structured JSON)
{"status": "success|partial|failed",
"hypotheses": [
{"statement": "...",
"rationale": "...",
"discriminating_test": "...",
"elo": 0,
"ai_generated": true}
],
"warnings": ["..."]}
④ Tool budget
physics_check · physics_compute · material_lookup · provenance_query only. Maximum 10 turns.
⑤ Source guide
- Read: the topic and context supplied in the task; material data via
material_lookup. - Do not read: the D2 anomaly-explanation code path — hypothesis generation (D1) is independent of it.
⑥ Boundaries · ambiguity
- Every hypothesis must be falsifiable and carry a concrete discriminating test.
- Every hypothesis carries
ai_generated: true— these are AI-proposed directions, never claimed results. - Reflect each hypothesis against the sanity oracle; drop any that violate known physics.
- Do not fabricate numbers or citations. Quantitative claims must come from tools.
- If the topic is too vague to ground, return
status: partialand state what is missing.
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.
- 1mo ago First seen · 50 lines · 40 tokens per session scan A 1dde9cb64bda
hypothesis-gen is an agent published in the GitHub repository TaewoooPark/MagLab (11 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 425 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 2026-08-30.
Other agents, from other repositories
stat-comparison-analyst
Statistical comparison agent. Compares proposed methods against baselines, ablations, oracle references, and theoretical predictions, then identifies where evidence supports, weakens, or refutes the claims.
stat-quality-auditor
Statistical research quality auditor. Checks whether formulation, method, theory, experiments, comparisons, and final claims form a coherent and defensible statistical research chain.
stat-result-synthesizer
Statistical result synthesis agent. Writes the final research narrative, combining formulation, proposed method, theory, experiments, comparisons, and limitations into a coherent report.
data-cruncher
Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.