fusion-spatial-mcp: Instructions file for Claude Code

CLAUDE.md

fusion-spatial-mcp CLAUDE.md is an instructions file for Claude Code from aphollis/fusion-spatial-mcp. It costs 427 tokens per session, scanned A, original, MIT.

Project instructions for building fusion-spatial-mcp, a tool that connects an AI agent to Autodesk Fusion design software for spatial and 3D work.

In plain words
What is it for?
Use them to follow the project's build plan, keep Fusion-specific concepts and units correct, and avoid running generated code in a user's live session without approval.
Why use it?
They impose a required build order and warn about project-specific rules, API units, and safe testing with a live Fusion session.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is aphollis/fusion-spatial-mcp's own configuration. It tells Claude Code how to work on fusion-spatial-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fusion-spatial-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aphollis/fusion-spatial-mcp. 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/aphollis/fusion-spatial-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aphollis/fusion-spatial-mcp

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.

agentmods badge for fusion-spatial-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aphollis/fusion-spatial-mcp/claude-md.svg)](https://agentmods.dev/instructions/aphollis/fusion-spatial-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aphollis/fusion-spatial-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aphollis/fusion-spatial-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 427 This file is loaded in full into every session.
When invoked 427 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00427 $0.00427
Opus 5 $0.00214 $0.00214
Sonnet 5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured 6d ago against content hash 69aae7e7291b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fusion-spatial-mcp 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 6d 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 · 30 lines

What it actually says

fusion-spatial-mcp — session context

Read docs/BUILD_PLAN.md FIRST — it is the authoritative, self-contained plan with milestones, acceptance gates, Fusion-specific traps, and pointers into the reference implementation. Follow its phase order (F0→F5); do not write spatial tool code before the F2 conformance gate passes.

Hard rules:

  • Design Fusion-native. This project is not a port of the Rhino server: tool vocabulary, workflows, and agent guidance come from Fusion's own concepts (timeline, features, constrained sketches, user parameters, components). The sibling checkout ../rhino-gh-mcp is an infrastructure donor only: a source of engineering patterns (TCP bridge, threading, token efficiency). spatial-core lives in its own sibling repo ../spatial-core (consumed via file: dependency — never fork/copy its source). Do not carry Grasshopper concepts or names across.
  • Never run generated code against the user's live Fusion session without asking first. Compile-check offline; batch live testing into agreed steps.
  • Fusion API traps: internal units are ALWAYS centimeters (convert to the design's default display unit at the adapter); documents are commonly Y-up (report the actual axis); use entityToken as body id; API calls only on the main thread via CustomEvent marshaling; listener binds WITHOUT SO_REUSEADDR.
  • This repo is public — no machine-specific paths or private details in committed files. Machine tooling notes live in session memory, not here. Validate add-in Python offline with any CPython 3.9+ py_compile.
  • Fusion 360 is installed (webdeploy production). Dev add-ins folder: %APPDATA%\Autodesk\Autodesk Fusion 360\API\AddIns\ (user has prior add-in experience — "Sheeter" add-in and the FusionRhinoBar project).
  • Commit per milestone with concise messages; push to origin (public repo).
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. 6d ago First seen · 30 lines · 427 tokens per session scan A 69aae7e7291b

Subscribe to this mod's changes

fusion-spatial-mcp CLAUDE.md is an instructions file published in the GitHub repository aphollis/fusion-spatial-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 427 tokens to every session, about $0.0021 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens