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 TianGzlab/OmicsClaw --skill sc-consensus-clusteringgit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote 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/tiangzlab/omicsclaw/sc-consensus-clustering)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-consensus-clustering"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-consensus-clustering/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/tiangzlab/omicsclaw/sc-consensus-clustering"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-consensus-clustering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00074 | $0.01095 |
| Opus 5 | $0.00037 | $0.00548 |
| Sonnet 5 | $0.00015 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
sc-consensus-clustering 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sc-consensus-clustering
When to use
The user has a preprocessed scRNA AnnData (PCA + neighborhood graph
already computed via sc-preprocessing) and wants robust cell-cluster
assignments insensitive to the chosen resolution. Single-resolution
Leiden/Louvain results are notoriously resolution-sensitive — at
r=0.4 you get 6 broad types, at r=1.5 you get 22 sub-states. This
skill runs a SACCELERATOR-style consensus across a resolution sweep
(and optionally across leiden vs louvain) and reports the stable
core of the labels.
It does NOT replace sc-clustering; it wraps it.
Inputs & Outputs
Inputs
- Modalities: scrna
- File types:
.h5ad - Requires a preprocessed AnnData (
Xnormalised, PCA/neighbours present) - Expects
obsm:X_pca
Outputs
consensus_labels.tsvmember_scores.csvcross_method_nmi.csvplan.jsonreport.mdresult.json
Flow
- Plan members — either user-supplied (
--members/--all) or derived from the resolution sweep × cluster-methods combinations. - Fan out — runtime invokes
sc-clusteringonce per member. - Score —
silhouette_scorefrom each member'sclustering_summary.csvis the intrinsic-quality signal; cross-method NMI is computed across members. - BC pick — top-K-by-composite-score default; CLI interactive override allowed.
- Consensus — kmode / weighted / LCA on the selected base clusterings.
- Report — banner + score table + NMI matrix.
Gotchas
--cluster-methodsdefaults toleidenONLY, not both, becauselouvainandleidenagree to within 1–2% on most datasets and the consensus signal comes mostly from the resolution sweep.- Resolutions must span at least one factor of 2 for the consensus to be informative; default sweep covers 0.5–2.0.
- The mandatory banner is enforced by
runtime/consensus/dispatch.output_banner. Do NOT strip it. requires_preprocessed: true— runsc-preprocessingfirst.
What ships with it
6 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.
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.
- 5d ago First seen · 115 lines · 74 tokens per session scan A ad1d43af59db
sc-consensus-clustering is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,095 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
Virtual Embryo — atlas data + knowledge graph
Query the Virtual Embryo knowledge graph (mouse/human developmental biology: genes, anatomy, Theiler/Carnegie stages, gene expression, diseases, papers) and its 3D atlas catalog (anatomical OPT/light-sheet volumes + 3D spatial- transcriptomics datasets), and visualise those datasets in 3D with the volume3d / spatial3d…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
neuropixels-analysis
Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…