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/zamushwani/biomedical-ai-skillsWrote 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/commands/zamushwani/biomedical-ai-skills/annotate-variants)<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/annotate-variants"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/annotate-variants/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/commands/zamushwani/biomedical-ai-skills/annotate-variants"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/annotate-variants.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 | $0.00035 | $0.00374 |
| Opus 5 | $0.00017 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
annotate-variants 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 11d 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
Annotate the variants in $0 for tumour type $1.
Follow the variant-annotation skill. Order matters:
- Normalize first:
bcftools norm -m -any -f <ref>. Un-normalized records fail knowledgebase lookups silently — the variant reads as absent, not as an error. - Then annotate (VEP/SnpEff), picking the transcript-selection rule deliberately and stating it.
- Then classify on the right axis. These are three separate frameworks:
ACMG/AMP 2015 germline pathogenicity germline only
ClinGen/CGC/VICC 2022 somatic oncogenicity is it driving?
AMP/ASCO/CAP 2017 clinical tiers does it change management?
Oncogenicity and actionability are different axes: KRAS G12D is unambiguously oncogenic and can still be Tier III where nothing acts on it.
- A tier requires a tumour type. BRAF V600E is Tier IA in melanoma and Tier IIC in colorectal. If
$1is empty, ask for it — do not assign tiers without it. - Use popmax, not global, allele frequency. 0.1% globally can be 4% in one ancestry group.
Report per variant: gene, HGVS, consequence, population AF (popmax), classification with the criteria applied, and the evidence source.
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.
- 11d ago First seen · 27 lines · 0 tokens per session scan A 2b2f6133ca7e
annotate-variants is a command published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 13d ago), licensed MIT. It adds 35 tokens to every session and 374 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
read
Accepts: local PDF path, DOI, journal URL, or a pasted abstract with basic metadata.
feed
Execute all steps without asking for user confirmation at intermediate stages. Report results at the end.
critic
Deep-review a specific cluster with CellTypePilot's Annotation Critic.
ctp-inspect
Inspect single-cell data — auto-detect species, tissue, clusters, embeddings.
faostat-country-profile
Generate a food security and agricultural profile for a country.
vehicle-comparison
Side-by-side comparison of launch vehicles — cost, payload, reusability.