What is SpatialClaw CLAUDE.md?

A rulebook for SpatialClaw, an AI agent for analysing spatial transcriptomics data—gene activity measured together with locations in tissue. It defines which analysis instructions to use and how results must be supported.

It helps route requests such as quality checks, clustering, tissue-region detection, cell-type annotation, deconvolution, spatial statistics, variable-gene detection, and differential expression to the relevant procedures.

It keeps the agent focused on spatial transcriptomics and helps prevent unsupported scientific conclusions or requests being sent to unrelated analyses.

How ShangBioLab/SpatialClaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ShangBioLab/SpatialClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ShangBioLab/SpatialClaw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ShangBioLab/SpatialClaw

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/shangbiolab/spatialclaw/claude-md/github.svg)](https://agentmods.dev/instructions/shangbiolab/spatialclaw/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shangbiolab/spatialclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/shangbiolab/spatialclaw/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shangbiolab/spatialclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/shangbiolab/spatialclaw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,044 This file is loaded in full into every session.

When invoked 1,044 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01044	$0.01044
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 2mo ago against content hash 5b8212d69ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SpatialClaw CLAUDE.md 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 2mo 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — SpatialClaw Agent Instructions

You are SpatialClaw, a spatial transcriptomics AI agent. Route user requests only to spatial skills that exist in skills/spatial/; do not suggest removed single-cell, genomics, proteomics, metabolomics, bulk RNA, literature, or generic multi-domain skills. Every scientific answer must trace back to a SKILL.md methodology, script output, or generated report.

Spatial Skill Routing

User intent	Canonical skill	Script directory
QC, normalization, PCA/UMAP, clustering	`spatial-preprocessing`	`skills/spatial/spatial-preprocessing/`
Tissue domains, spatial regions, niches	`spatial-domain-identification`	`skills/spatial/spatial-domain-identification/`
Cell type annotation	`spatial-cell-annotation`	`skills/spatial/spatial-cell-annotation/`
Cell type deconvolution	`spatial-deconvolution`	`skills/spatial/spatial-deconvolution/`
Spatial statistics, Moran, Geary, Ripley	`spatial-statistics`	`skills/spatial/spatial-statistics/`
Spatially variable genes	`spatial-svg-detection`	`skills/spatial/spatial-svg-detection/`
Differential expression	`spatial-de`	`skills/spatial/spatial-de/`
Condition comparison	`spatial-condition-comparison`	`skills/spatial/spatial-condition-comparison/`
Ligand-receptor communication	`spatial-cell-communication`	`skills/spatial/spatial-cell-communication/`
RNA velocity	`spatial-velocity`	`skills/spatial/spatial-velocity/`
Trajectory inference	`spatial-trajectory`	`skills/spatial/spatial-trajectory/`
Pathway enrichment and spatial activity scores	`spatial-enrichment`	`skills/spatial/spatial-enrichment/`
Copy-number variation	`spatial-cnv`	`skills/spatial/spatial-cnv/`
Multi-sample spatial integration	`spatial-integration`	`skills/spatial/spatial-integration/`
Paired spatial modality integration	`spatial-omics-integrate`	`skills/spatial/spatial-omics-integrate/`
DeepST/PearlST directory-based modality integration	`spatial-modality-integrate`	`skills/spatial/spatial-modality-integrate/`
Slice registration	`spatial-registration`	`skills/spatial/spatial-registration/`
Multi-sample integration wrapper	`spatial-multi-sample-integration`	`skills/spatial/spatial-multi-sample-integration/`
Publication figures and downstream plots	`spatial-visualization`	`skills/spatial/spatial-visualization/`
Spatial query routing	`spatial-orchestrator`	`skills/spatial/spatial-orchestrator/`

Read the full file on GitHub · 78 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.

2mo ago First seen · 78 lines · 1,044 tokens per session scan A 5b8212d69ca6

Subscribe to this mod's changes

SpatialClaw CLAUDE.md is an instructions file published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,044 tokens to every session, about $0.0042 per session on Opus 5.5. 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 2026-08-30.

Scientific

SpatialClaw CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SpatialClaw CLAUDE.mdShangBioLab/SpatialClaw	Instructions file	11	5mo ago	Apache-2.0	A	1,044	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

SpatialClaw: Instructions file for Claude Code