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 agentlas-ai/agentlas-desktop --skill hypogenicgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/hypogenic)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/hypogenic"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/hypogenic/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/agentlas-ai/agentlas-desktop/hypogenic"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/hypogenic.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 | $0.00062 | $0.02899 |
| Opus 5.5 | $0.00025 | $0.01160 |
| Sonnet 5.5 | $0.00012 | $0.00580 |
| Haiku 4.5 | $0.00006 | $0.00290 |
Grade A, and why
hypogenic 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.
This is a copy
91% identical to hypogenic — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HypoGeniC
Scope and scientific boundary
This skill covers the ChicagoHAI software repository
ChicagoHAI/hypothesis-generation and PyPI package hypogenic.
HypoGeniC iteratively proposes and scores textual patterns from labeled data;
HypoRefine adds literature-derived information; union workflows combine banks.
Keep these boundaries explicit:
- The output is a bank of candidate textual hypotheses and task-prediction statistics. It is not experimental confirmation, causal evidence, a clinical conclusion, or proof of scientific novelty.
- Predictive accuracy on held-out examples assesses task utility, not truth of a mechanism. Independent scientific validation still needs domain review, suitable controls, preregistered tests where appropriate, and new evidence.
- For researcher-led formulation of mechanisms and falsifiable predictions,
use
../hypothesis-generation/SKILL.md. For open-ended ideation, use the scientific brainstorming skill.
Default workflow: local review first
Never start a model call automatically.
- Classify the request: HypoGeniC software use, general hypothesis formulation, or downstream scientific validation.
- Record the exact package, source, dataset, model/provider, destination, split policy, output path, and budgets.
- Validate the local run policy and official task config.
- Audit dataset checksums, schemas, duplicates, and split leakage.
- Generate a bounded cost/run plan. Review provider retention and current pricing outside the package.
- Ask for separate confirmation before any external LLM call, model download, or upload of dataset text.
- Inspect the resulting hypothesis bank locally.
- Evaluate once on the preserved test split and report limitations.
The bundled scripts are deterministic, bounded, local-only, and never import
hypogenic, contact a model, load .env, enumerate the environment, or execute
text found in configs, datasets, hypotheses, or results.
Reproducible installation
What ships with it
17 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/dataset_manifest.example.json 874 B
- assets/result.example.json 448 B
- assets/run_config.example.json 1.2 KB
- assets/task_config.example.yaml 1.3 KB
- references/configuration.md 5.0 KB
- references/datasets.md 6.1 KB
- references/evaluation.md 5.2 KB
- references/security.md 7.3 KB
- references/sources.md 7.4 KB
- references/upstream.md 7.8 KB
- scripts/__init__.py 64 B runs code
- scripts/_common.py 44 KB runs code
- scripts/audit_dataset.py 13 KB runs code
- scripts/evaluate_local.py 7.7 KB runs code
- scripts/inspect_outputs.py 5.6 KB runs code
- scripts/plan_run.py 8.2 KB runs code
- scripts/validate_config.py 5.7 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.
- 1mo ago First seen · 308 lines · 62 tokens per session scan A dc3095345cb1
hypogenic is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 2,899 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to hypogenic, differing in 38 lines, and is treated as a copy.
Other skills, from other repositories
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
reactome-database
Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways)…
borzoi
Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.