image_studio_mcp: Instructions file for Claude Code

CLAUDE.md

image_studio_mcp CLAUDE.md is an instructions file for Claude Code from ross-sec/image_studio_mcp. It costs 1,601 tokens per session, scanned A, original, MIT.

Tools for controlling the STAAD.Pro display, including interface modes, camera views, visible elements, labels, result diagrams, annotations, and saved views.

In plain words
What is it for?
Use it to switch between modeling and post-processing, show standard views, rotate and zoom, hide or select members and other elements, adjust display scales, and export images.
Why use it?
It lets an automated workflow present and capture the model or its results in a chosen view without manual window control.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is ross-sec/image_studio_mcp's own configuration. It tells Claude Code how to work on image_studio_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 image_studio_mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ross-sec/image_studio_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/ross-sec/image_studio_mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ross-sec/image_studio_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 image_studio_mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ross-sec/image_studio_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ross-sec/image_studio_mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ross-sec/image_studio_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ross-sec/image_studio_mcp/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.

agentmods 80×15 button for image_studio_mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ross-sec/image_studio_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ross-sec/image_studio_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,601 This file is loaded in full into every session.
When invoked 1,601 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 $0.01601 $0.01601
Opus 5.5 $0.00640 $0.00640
Sonnet 5.5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 2mo ago against content hash fef3454ca6ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

image_studio_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 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A thin MCP server that wraps the remote Image Studio /v1 HTTP API (text→image + image edit) as agent tools. It does no local image processing — no sharp/jimp/canvas, no model SDKs. All inference runs on the backend (studio.ross-developers.com); this server submits jobs, polls them to a terminal state, and returns each result PNG inline (base64) while also saving it to disk. TypeScript, ESM, ~400 LOC across 5 files. Single transport: stdio (launched by the MCP client).

Published to npm as @ross_technologies/image_studio_mcp (bin: image_studio_mcp, unscoped); the supported end-user flow is npx @ross_technologies/image_studio_mcp + their own IMAGE_STUDIO_API_KEY (from https://studio.ross-developers.com), no clone/build. Name is scoped because npm's typosquat filter blocks the unscoped form as "too similar" to an existing image-studio-mcp. It is a first-party client of the hosted Image Studio API — it always targets the remote backend (IMAGE_STUDIO_URL, default studio.ross-developers.com). Self-hosting the image backend is not a supported path; treat IMAGE_STUDIO_URL overrides as internal dev/testing only and keep them out of public docs.

Commands

npm run build         # tsc → dist/ (emits JS + .d.ts + sourcemaps)
npm run dev           # tsx src/stdio.ts   — run from source, no build
npm run start         # node dist/stdio.js — built server (the bin / agent launch target)
npm run clean         # cross-platform node one-liner (works on Windows + Unix)
  • No tests and no linter exist — no test runner, no eslint/prettier/biome, no CI. Do not invent npm test/npm run lint. The only verification gate (per CONTRIBUTING.md) is that npm run build passes cleanly, plus a manual stdio tools/list / tools/call transcript.
  • NodeNext ESM: source imports of sibling modules must carry the .js suffix even though the files are .ts (e.g. import { buildServer } from "./server.js"). Node >=20.
  • Build with npm, not pnpm, on NTFS/exFAT mounts (pnpm's symlink store breaks there). package-lock.json is the committed lockfile.

Read the full file on GitHub · 70 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. 2mo ago First seen · 70 lines · 1,601 tokens per session scan A fef3454ca6ed

Subscribe to this mod's changes

image_studio_mcp CLAUDE.md is an instructions file published in the GitHub repository ross-sec/image_studio_mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,601 tokens to every session, about $0.0064 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 2026-08-31.

Related

image_studio_mcp CLAUDE.md compared with instructions from other repositories

image_studio_mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
image_studio_mcp CLAUDE.mdross-sec/image_studio_mcpInstructions file04mo agoMITA1,601Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot