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 agentmods add instructions/shangbiolab/spatialclaw/agents-mdgit clone --depth 1 https://github.com/ShangBioLab/SpatialClawWhat 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 | $0.01687 | $0.01687 |
| Opus 5 | $0.00843 | $0.00843 |
| Sonnet 5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
SpatialClaw AGENTS.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 2d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — SpatialClaw Guide for AI Coding Agents
This guide is for AI coding agents working on the SpatialClaw codebase.
Project Overview
SpatialClaw is a spatial transcriptomics analysis platform. The current architecture is spatial-only: non-spatial omics skills and cross-domain orchestrators have been removed. Each remaining skill is a self-contained module that runs through the CLI or Python APIs, with local-first processing and standardized reports.
The main package is spatialclaw/, and the root script is spatialclaw.py.
Installed commands are spatialclaw, sc, spatialclaw-chat, and sc-chat.
Setup
cd /lanou/Claw/SpatialClaw
pip install -e .
python spatialclaw.py list
python spatialclaw.py run spatial-preprocessing --demo
spatialclaw list
sc list
spatialclaw run spatial-preprocessing --demo
sc run spatial-preprocessing --demo
Commands
| Command | Purpose |
|---|---|
python spatialclaw.py list |
List registered spatial skills |
python spatialclaw.py run <canonical-skill> --demo |
Run a skill demo when that skill registers demo_args |
python spatialclaw.py run <canonical-skill> --input <file> --output <dir> |
Run with user data |
python spatialclaw.py interactive |
Start interactive terminal chat |
python spatialclaw.py interactive --ui tui |
Start full-screen Textual TUI |
python spatialclaw.py interactive -p "<prompt>" |
Single-shot LLM/tool mode |
spatialclaw-chat -p "<prompt>" |
Direct chat alias for spatialclaw interactive -p |
sc-chat -p "<prompt>" |
Short direct chat alias |
sc list |
Short alias for spatialclaw list |
python spatialclaw.py interactive --session <id> |
Resume a previous session |
python spatialclaw.py tui |
Start the TUI |
python spatialclaw.py mcp list |
List configured MCP servers |
python spatialclaw.py mcp add <name> <cmd> [args] |
Add an MCP server |
python spatialclaw.py mcp remove <name> |
Remove an MCP server |
python spatialclaw.py mcp config |
Show MCP config file path |
python spatialclaw.py onboard |
Run interactive setup wizard |
python spatialclaw.py memory-server |
Start graph memory REST API |
python -m pytest -v |
Run tests |
make demo |
Run the spatial preprocessing demo |
make bot-telegram |
Start Telegram bot |
make bot-feishu |
Start Feishu bot |
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.
- 2d ago First seen · 171 lines · 1,687 tokens per session scan A 37016b9c9a50
SpatialClaw AGENTS.md is an instructions file published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,687 tokens to every session, about $0.0084 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.