orchestrator

orchestrator is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 60 tokens per session (1,232 once invoked), scanned A, original, Apache-2.0.

A router for natural-language omics questions. Omics is the study of large biological datasets such as genes, proteins, and metabolites; this tool chooses the appropriate specialised workflow across those areas.

In plain words
What is it for?
Use it to route questions about spatial data, single-cell data, genomics, proteomics, metabolomics, or bulk RNA analysis to the relevant skill.
Why use it?
It reduces the need to know which analysis tool matches a biology question. It can use keywords, a language-model match, or both when the request is unclear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to route questions about spatial data, single-cell data, genomics, proteomics, metabolomics, or bulk RNA analysis to the relevant skill.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tiangzlab/omicsclaw/orchestrator
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.

Any agent
npx skills add TianGzlab/OmicsClaw --skill orchestrator
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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/orchestrator.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/orchestrator"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
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 5.1 $0.00060 $0.01232
Opus 5 $0.00030 $0.00616
Sonnet 5 $0.00012 $0.00246
Haiku 4.5 $0.00006 $0.00123

Measured 4d ago against content hash 1f9f51afe799, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orchestrator 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (omics_orchestrator.py, omics-skill-builder/omics_skill_builder.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/orchestrator/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orchestrator

When to use

The user asks a natural-language omics question (e.g. "find spatial domains in my Visium data", "call CNVs from this BAM", "run DE on my proteomics CSV") and you need to dispatch to the correct skill across the 6 routed OmicsClaw domains (_DOMAINS at omics_orchestrator.py:190). Three routing modes:

  • keyword (default) — fast lexical match against trigger_keywords in every skill's skill.yaml.
  • llm — LLM-based query → skill match (slower, more flexible).
  • hybrid — keyword first, LLM fallback when ambiguous.

If the target skill is already known, invoke it directly — this skill exists to dispatch ambiguous queries, not as a wrapper. For scaffolding NEW skills use omics-skill-builder.

Inputs & Outputs

Outputs

  • result.json
  • demo_report.txt
  • Produces artifact orchestrator.route_decision as result.json (json)

Flow

  1. Parse --query (or --demo).
  2. If --input is provided, call detect_domain_from_path (omicsclaw.loaders) to bias domain selection.
  3. Dispatch to route_keyword / route_query_unified per --routing-mode (omics_orchestrator.py:24-26 imports).
  4. Resolve the chosen skill via resolve_capability (omicsclaw.core.capability_resolver); look up registry entry via omicsclaw.core.registry.registry.
  5. Write result.json (omics_orchestrator.py:409); print the selected skill name + suggested CLI invocation.

Gotchas

  • --query REQUIRED unless --demo. No explicit raise — argparse accepts a None query, the run still exits 0 and writes result.json with detected_skill: null, coverage: "no_skill". Always pass --query for real use.
  • --routing-mode is IGNORED when --query is set. omics_orchestrator.py:374-389 dispatches --query runs to resolve_capability (capability-resolver — keyword-based with no mode parameter). --routing-mode only takes effect for file-only routing (:393 route_query_with_mode) and --demo (:362 run_demo). For LLM-routed queries, call the unified router directly.
  • Missing LLM_API_KEY SILENTLY falls back to keyword routing — no error. omicsclaw/routing/llm_router.py:48-50 logs a warning and returns (None, 0.0); the orchestrator continues with keyword/capability routing. The run still exits 0 — inspect logs to confirm which mode actually fired.
  • keyword mode depends on trigger_keywords in skill.yaml. Stale or missing keywords degrade routing quality silently. The 95 v2 skills' keyword tables are loaded on every call via the registry.
  • No analysis is performed. This skill only emits a routing decision in result.json; it does NOT execute the chosen downstream skill. The user (or a wrapping orchestration script) must invoke it.
  • Demo and real-query outputs are mutually exclusive. --demo writes ONLY output_dir/demo_report.txt and returns at omics_orchestrator.py:363; real --query / --input runs write ONLY output_dir/result.json (:409). The two never co-exist in the same run.

Read the full file on GitHub · 93 lines

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. 4d ago First seen · 93 lines · 60 tokens per session scan A 1f9f51afe799

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,232 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…

synthetic-sciences/openscience · 68 tokens

cellxgene-census-query

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…

PharMolix/OpenBioMed · 105 tokens

single-cell-scrna-seq-analysis-scanpy

Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…

PharMolix/OpenBioMed · 85 tokens

single-cell-multi-omics-analysis-scvi

Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…

PharMolix/OpenBioMed · 94 tokens

anndata

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

synthetic-sciences/openscience · 63 tokens

celltypepilot

Single-cell cell-type annotation with evidence, conservative abstention, and reviewable drafts. Use this whenever the user wants to annotate, label, or identify cell types for pre-clustered single-cell or spatial transcriptomics data (.h5ad), or says things like "annotate my clusters", "what cell types are these?"…

HERRY423/CellTypePilot · 151 tokens