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/qc-single-cell)<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/qc-single-cell"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/qc-single-cell/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/qc-single-cell"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/qc-single-cell.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 | $0.00045 | $0.00303 |
| Opus 5 | $0.00023 | $0.00151 |
| Sonnet 5 | $0.00009 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
qc-single-cell 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
Run QC on $0.
Follow the single-cell-atlas skill. The parts that are usually got wrong:
- Use MAD-based thresholds, not fixed cutoffs. A hard
n_genes > 200throws away real cells in low-complexity tissue and keeps debris in others. Compute median absolute deviation per metric and justify the multiplier. - Mitochondrial percentage is tissue-dependent. A 5% cutoff is convention, not biology; cardiomyocytes and hepatocytes legitimately run far higher.
- Detect doublets before clustering, not after. A doublet cluster looks like a novel intermediate cell type and gets written up as one.
- Report the filter cascade — cells in, cells removed by each criterion, cells out. A single "after QC" number hides which filter did the damage.
- Filter genes on cells-expressing, not total counts.
Report: the cascade table, the MAD thresholds actually used with their multipliers, doublet rate, and a before/after QC plot.
If $0 is empty, ask which matrix to load.
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 · 20 lines · 45 tokens per session scan A 4bd429ffd403
qc-single-cell is a command published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 303 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.