agentmods.dev

consensus-domains

consensus-domains is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 73 tokens per session (1,508 once invoked), scanned A, original, Apache-2.0.

A workflow that combines several methods for identifying spatial tissue domains, such as regions with distinct gene-activity patterns. It compares the methods, creates a consensus assignment, and records where they disagree.

In plain words
What is it for?
Use it to create verified tissue-domain labels for downstream cell-type analysis, region-specific gene comparisons, or figures.
Why use it?
It reduces reliance on one domain-detection method when results differ across methods or the tissue is difficult to classify. The disagreement information shows where the result is less certain.

Skill for Claude CodeCodex

not rated 160 1mo ago A scan 73 tokens original Apache-2.0
View the source file TianGzlab/OmicsClaw
Install

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.

agentmods
npx agentmods add skills/tiangzlab/omicsclaw/consensus-domains
Any agent
npx skills add TianGzlab/OmicsClaw --skill consensus-domains
Clone the repo
git clone --depth 1 https://github.com/TianGzlab/OmicsClaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for consensus-domains

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/consensus-domains.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/consensus-domains)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/consensus-domains"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/consensus-domains.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,508 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01508
Opus 5 $0.00036 $0.00754
Sonnet 5 $0.00015 $0.00302
Haiku 4.5 $0.00007 $0.00151

Measured yesterday against content hash 1c799e222571, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consensus-domains 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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (consensus_domains.py, tests/test_cli_smoke.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/spatial/consensus-domains/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

consensus-domains

When to use

The user has a preprocessed spatial AnnData (typically already QC'd via spatial-preprocess) and wants a more trustworthy tissue-domain assignment than any single method can produce — because the user knows single-method results disagree on cancer / non-standard tissues, or because the analysis is going to drive a downstream decision (cell-type deconvolution, region-specific DE, paper figure).

This skill fans out spatial-domains over N method choices, computes a typed statistical consensus, and surfaces the cross-method disagreement explicitly. It does NOT replace spatial-domains; it wraps it.

Inputs & Outputs

Inputs

  • File types: .h5ad
  • Requires a preprocessed AnnData (X normalised, PCA/neighbours present)

Outputs

  • consensus_labels.tsv
  • member_scores.csv
  • member_intrinsic_panel.csv
  • cross_method_nmi.csv
  • plan.json
  • report.md
  • result.json

Flow

  1. Plan — runtime/consensus/plan.propose_members reads spatial-domains' param_hints (from its skill.yaml), queries the evaluation-chair LLM (or falls back deterministically), produces N PlannedMember entries.
  2. Fan out — runtime/consensus/team.run_team invokes omicsclaw.skill.runner.run_skill("spatial-domains", ...) per member with max_parallel = min(N, cpu_count//2, 4) and a 600 s per-member timeout. cancel_event is propagated through.
  3. Score — runtime/consensus/scoring.score_all_members ranks survivors by composite alpha * cross_NMI + beta * mean_local_purity with the max_class_frac > 0.8 hard filter.
  4. BC pick — on the CLI surface in interactive mode, prompt the user with the top-K-by-score default; on Desktop/Channel surfaces (or --non-interactive), accept the default.
  5. Consensus — invoke the chosen operator (kmode / weighted / lca) on the selected base clusterings.
  6. Report — write report.md starting with the mandatory ADR 0010 banner; persist plan.json for audit; ready for graph-memory storage under analysis://typed/<run_id>.

Read the full file on GitHub · 143 lines

Files

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.

Changes

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.

  1. yesterday First seen · 143 lines · 73 tokens per session scan A 1c799e222571

Subscribe to this mod's changes

consensus-domains is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,508 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.

Scientificbc-rankingbioinformaticsconsensusexpert-in-the-loopkmodeknowledge-graphlcallm-agentsacceleratorspatialtyped-consensusweighted
Related

Other skills, from other repositories

clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

K-Dense-AI/scientific-agent-skills · 50 tokens

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…

K-Dense-AI/scientific-agent-skills · 83 tokens

geomaster

Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing…

K-Dense-AI/scientific-agent-skills · 148 tokens

datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…

K-Dense-AI/scientific-agent-skills · 67 tokens

deepspot-m

Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…

K-Dense-AI/scientific-agent-skills · 80 tokens

datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…

synthetic-sciences/openscience · 67 tokens