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/codex-curator/studiomcphub/claude-mdgit clone --depth 1 https://github.com/codex-curator/studiomcphubWrote 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/codex-curator/studiomcphub/claude-md)<a href="https://agentmods.dev/instructions/codex-curator/studiomcphub/claude-md"><img src="https://agentmods.dev/badge/instructions/codex-curator/studiomcphub/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 | $0.01906 | $0.01906 |
| Opus 5 | $0.00953 | $0.00953 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
studiomcphub 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md -- StudioMCPHub
What this is: An MCP (Model Context Protocol) server hub offering creative AI tools as paid services for autonomous AI agents and local assistants. Built by AI, for AI.
Domain: studiomcphub.com
Parent company: Metavolve Labs, Inc.
Sibling product: golden-codex.com (human-facing SaaS studio)
GCP project: the-golden-codex-1111
Canonical path (WSL): /mnt/c/Users/atmta/source/repos/studiomcphub.com/
Human partner: Tad MacPherson ([email protected])
Mission
The creative infrastructure layer for the AI age. Every agent deserves a studio.
StudioMCPHub exposes the Golden Codex pipeline as discoverable, pay-per-call MCP tools. AI agents connect, create, and pay -- no accounts required.
Architecture
┌─────────────────────────────────────────────────────────┐
│ studiomcphub.com │
│ (Cloud Run + Streamable HTTP) │
├─────────────────────────────────────────────────────────┤
│ MCP Server (FastMCP / Python) │
│ ├── generate_image — SD 3.5 Large + T5-XXL │
│ ├── upscale_image — ESRGAN x4 (L4 GPU) │
│ ├── enrich_metadata — Nova (Gemini 2.5/3.0 Pro) │
│ ├── infuse_metadata — Atlas (ExifTool + XMP) │
│ ├── register_hash — Aegis (pHash + LSH index) │
│ ├── store_permanent — Archivus (Arweave L1) │
│ ├── mint_nft — Mintra (Polygon) │
│ ├── verify_provenance — Aegis (strip-proof lookup) │
│ └── full_pipeline — All stages, one call │
├─────────────────────────────────────────────────────────┤
│ Payment Layer │
│ ├── x402 (USDC on Base) — Agent-native, no accounts │
│ ├── Stripe per-call — Traditional payment rails │
│ └── GCX Credits — Pre-purchased token balance │
├─────────────────────────────────────────────────────────┤
│ Discovery │
│ ├── /.well-known/mcp.json — MCP Server Card │
│ ├── /llms.txt — LLM-readable docs │
│ ├── /glama.json — Glama auto-discovery │
│ └── Smithery / PulseMCP / mcp.so listings │
└─────────────────────────────────────────────────────────┘
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.
- 4d ago First seen · 197 lines · 1,906 tokens per session scan A 55ee6047b1f3
studiomcphub CLAUDE.md is an instructions file published in the GitHub repository codex-curator/studiomcphub (7 stars, last pushed 19d ago), licensed MIT. It adds 1,906 tokens to every session, about $0.0095 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
p3a CLAUDE.md
Claude Code instructions for fabkury/p3a, covering claude.md and claude code notes.
p3a AGENTS.md
AGENTS.md instructions for fabkury/p3a, covering agents.md, project overview, ground rules, toolchain and environment and build commands.
codex-image-context-runtime AGENTS.md
Instructions for shixinnt/codex-image-context-runtime, covering agents.md, public boundary, runtime contract and changes.
openai-compatible-imagegen AGENTS.md
Instructions for Syh1906/openai-compatible-imagegen, covering agent instructions, project scope, package management, checks and module boundaries.
diffusers AGENTS.md
AGENTS.md instructions for huggingface/diffusers, a project described as: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
comfyui_mcp AGENTS.md
AGENTS.md instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.