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 exon-research/genomi --skill genomilabgit clone --depth 1 https://github.com/exon-research/genomiWrote 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/exon-research/genomi/genomilab)<a href="https://agentmods.dev/skills/exon-research/genomi/genomilab"><img src="https://agentmods.dev/badge/skills/exon-research/genomi/genomilab/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/exon-research/genomi/genomilab"><img src="https://agentmods.dev/badge/skills/exon-research/genomi/genomilab.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 | $0.00072 | $0.03452 |
| Opus 5.5 | $0.00029 | $0.01381 |
| Sonnet 5.5 | $0.00014 | $0.00690 |
| Haiku 4.5 | $0.00007 | $0.00345 |
Grade A, and why
genomilab 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.
How it starts
The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GenomiLab Research Desk
Keep the current host agent in control of the conversation, native specialist subagents, planning, streaming, follow-ups, and cancellation. Use GenomiLab for typed capabilities, patient authorization, Active Genome Index access, durable evidence and hypothesis state, validated briefs, and the patient portal.
The portal is for patient onboarding, exact approvals, integration setup, and monitoring committed investigation milestones. Never start a second agent task from the portal.
Start or resume
- Call
genomilab.open_workspace. - If it returns
status="setup_required", keep setup in core Genomi. Select or finish the current user's Active Genome Index. If none exists, ask the user for the local VCF or another supported genome-source path and use core Genomi intake; pointing the host at that path is the only genome handoff. Do not open an investigation without a query-ready selected index. - Show the returned portal link when the patient needs onboarding or approval.
- Call
genomilab.create_investigationfor a new question, orgenomilab.inspect_investigationfor an existing investigation. - If no profile observation exists, ask for one concise patient-reported fact before preparing authorization. Do not fabricate a symptom, diagnosis, phenotype, family history, or molecular finding.
Do not ask for a VCF path in GenomiLab. Genome intake remains in core Genomi; GenomiLab uses the selected Active Genome Index.
Chair the specialist board
For every new investigation, act as chair and form 2–5 native host subagents
with adaptive, non-overlapping domain roles. Give each specialist an explicit
role and bounded task chosen for the question; do not use a fixed board when a
different evidence mix is more relevant. Use stable logical specialist_id
values, not native task or thread identifiers. Record the board once with
genomilab.form_specialist_board before submitting a plan. These are persistent
specialist identities: reuse the same IDs in every investigation round, while
giving each specialist a new bounded assignment for that round.
What ships with it
1 file 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.
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 · 347 lines · 72 tokens per session scan A f486ca16cc4c
genomilab is a skill published in the GitHub repository exon-research/genomi (485 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 3,452 once invoked, about $0.0003 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 skills, from other repositories
autoresearch
Canonical around-the-clock research loop. Defines the agent's outer loop — read taste corpus + queue, pick the next experiment, mutate the explicitly-declared mutation surface, run the experiment under a hard time budget against a frozen metric, score, codify, repeat. Augmented with Karpathy's sharp primitives (frozen…
experiment
Run a materials-science / ML compute job on Rockie GPU capacity. Trigger words "run experiment", "submit job", "/experiment", or requests to quote/approve GPU spend before an experiment. Picks the right GPU type and count from a natural-language description (DFT for QE/VASP/ABINIT, MD for GROMACS/LAMMPS/OpenMM…
physics
Route physics simulation, modeling, validation, and research-compute requests across force fields, molecular dynamics, electronic structure, particle transport/collision, continuum multiphysics, plasma/PIC, nuclear/radiation, and astro/cosmology. Use open-source-first engines, refuse local heavyweight execution on the…
sota-delta
Track 3 quickstart wrapper that reproduces a paper or repository baseline on Rockie GPU, then extends it with a user-specified delta and compares baseline versus delta.
post-run-review
After an experiment finishes, structured review emits {isbug, failureclass, summary, metric, lowerisbetter}, auto-closes the journal node, emits a [LEARN] block when isbug=true, and files a [DEAD-END] when the failureclass is "bad-hypothesis". Use immediately after any training/eval run — the agent invokes this…
queue-refill
Refill the experiment queue when it drops below target (default 5 pending items). Brainstorms 3–5 new high-quality experiments informed by recent [LEARN] rules, killed dead-ends, best-so-far results, and hypothesis-calibration drift. Use when queue.py refill-needed returns non-zero, when the user asks "what should we…