Borrowing it
Nothing to install: this file belongs to VXNTedits/fusion360-mcp-periscope. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VXNTedits/fusion360-mcp-periscope/main/AGENTS.mdgit clone --depth 1 https://github.com/VXNTedits/fusion360-mcp-periscopeWrote 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.
[](https://agentmods.dev/instructions/vxntedits/fusion360-mcp-periscope/agents-md)<a href="https://agentmods.dev/instructions/vxntedits/fusion360-mcp-periscope/agents-md"><img src="https://agentmods.dev/badge/instructions/vxntedits/fusion360-mcp-periscope/agents-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.
<a href="https://agentmods.dev/instructions/vxntedits/fusion360-mcp-periscope/agents-md"><img src="https://agentmods.dev/badge/instructions/vxntedits/fusion360-mcp-periscope/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
fusion360-mcp-periscope 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 9d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PERISCOPE — Instructions for AI agents
You are talking to a live Autodesk Fusion session through strictly read-only tools. You cannot modify the design, and nothing you do needs user confirmation on safety grounds. This file tells you how to get correct answers cheaply.
Getting connected
- As an MCP client: twelve stdio tools, registered per the README. Start
with
fusion_healthwhenever anything misbehaves — it answers even when Fusion is busy or closed, and its error objects contain the exact fix. - Direct HTTP (for shells/scripts):
http://127.0.0.1:8735withAuthorization: Bearer <token>. The token file lives beside the installed add-in:%APPDATA%\Autodesk\Autodesk Fusion 360\API\AddIns\Periscope\token. Endpoints mirror the tools:/health /session /tree /joints /rigid_groups /constraints /timeline /parameters /measure /geometry_context /selection /viewport /probe(GET only).entity_tokenstakes a URL-encoded JSON array. - One-shot everything-dump:
python install/verify.py --save <dir> --probe.
The discipline that matters most
Measure; don't infer. The tool surface exists because AI models reconstruct physical dimensions from nominal parameters, constraint intent, mirror features, and viewport appearance — and get them plausibly, expensively wrong.
- For any physical size, extent, clearance, or spacing: use
get_geometry_context(evaluated precise bounds) ormeasure(MeasureManager). These reflect what downstream split/remove/pattern features actually left behind. - Parameters are design intent, not results. A
1000 mmextrusion parameter is not the length of the part if a later feature cut it down. Treatget_parametersvalues as nominal until evaluated geometry confirms them. - Every numeric result is classified
fusion_measured,fusion_reported, orderived_from_fusion_geometry. Propagate these labels into your answers. If you do arithmetic on reported values, say so and show the formula. - Never claim exact parallelism, orthogonality, or symmetry from a viewport image, a rigid group, a mirror feature, healthy constraints, or zero offsets alone. Those prove intent. Only measurement proves position — sub-0.1 mm assembly shifts are real, invisible in all of the above, and expensive.
- If a direct measurement isn't available, state the limitation. Do not fill the gap with plausible CAD reasoning presented as fact.
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.
- 9d ago First seen · 86 lines · 1,158 tokens per session scan A ac2a6cc43da9
fusion360-mcp-periscope AGENTS.md is an instructions file published in the GitHub repository VXNTedits/fusion360-mcp-periscope (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 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.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.