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/ross-sec/image_studio_mcp/claude-mdgit clone --depth 1 https://github.com/ross-sec/image_studio_mcpWrote 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/ross-sec/image_studio_mcp/claude-md)<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="Measured on agentmods" 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 | $0.01601 | $0.01601 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
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 5d 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 — 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 thatnpm run buildpasses cleanly, plus a manual stdiotools/list/tools/calltranscript. - NodeNext ESM: source imports of sibling modules must carry the
.jssuffix even though the files are.ts(e.g.import { buildServer } from "./server.js"). Node>=20. - Build with
npm, notpnpm, on NTFS/exFAT mounts (pnpm's symlink store breaks there).package-lock.jsonis the committed lockfile.
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.
- 5d ago First seen · 70 lines · 1,601 tokens per session scan A fef3454ca6ed
image_studio_mcp CLAUDE.md is an instructions file published in the GitHub repository ross-sec/image_studio_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,601 tokens to every session, about $0.0080 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
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.
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).
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.
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.
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.