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/decocms/studio/agents-mdgit clone --depth 1 https://github.com/decocms/studioWhat 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 | $0.08900 | $0.08900 |
| Opus 5 | $0.04450 | $0.04450 |
| Sonnet 5 | $0.01780 | $0.01780 |
| Haiku 4.5 | $0.00890 | $0.00890 |
Grade A, and why
studio 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 yesterday.
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 — 685 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This file provides guidance when working with code in this repository, including for Claude Code (claude.ai/code) and other AI coding assistants.
Documentation Philosophy
IMPORTANT: The documentation in apps/docs/ describes the intended system design and behavior, not necessarily the current implementation state. Documentation represents the target architecture and how the system should work, serving as both specification and aspiration. When implementation and documentation differ, the documentation defines the goal, not a bug to be "fixed" in the docs.
Overview
Studio is an open-source control plane for Model Context Protocol (MCP) traffic. It provides a unified layer for authentication, routing, and observability between MCP clients (Cursor, Claude, VS Code) and MCP servers. The system is built as a monorepo using Bun workspaces with TypeScript, Hono (API), and React 19 (UI).
Commands
Development
# Start full dev environment (migrations + client + server)
bun run dev
# Start Studio client only (Vite dev server on port 4000)
bun run --cwd=apps/web dev
# Start Studio server only (Hono with hot reload)
bun run --cwd=apps/api dev:server
# Run documentation site locally
bun run docs:dev
# Native desktop app (Tauri) dev loop — HMR via Vite on port 4420
bun run --cwd=apps/native dev
One-time macOS setup for apps/native devs: run
bun run --cwd=apps/native dev:signing:setup once. It creates or reuses the
local self-signed decocms-dev code-signing identity; no Apple Developer
account is required. It also builds, signs, and installs one fixed
decocms-keychain-helper under the user's Application Support directory.
Debug app rebuilds talk to that unchanged helper over JSON stdin/stdout, so
Keychain sees one stable executable; tokens never use argv, logs, or a
filesystem fallback. The native dev runner still signs the app itself and
fails closed if signing drifts, but the fixed helper—not the app's self-signed
designated requirement—is what makes debug Keychain access stable. On every OS
debug sessions stay in the com.decocms.studio.dev namespace and release
sessions in com.decocms.studio, always inside an OS credential store (macOS
Keychain, Linux Secret Service) and never a file—only the fixed-helper detour
is macOS-debug-specific.
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.
- yesterday First seen · 685 lines · 8,900 tokens per session scan A 8004f1291e78
studio AGENTS.md is an instructions file published in the GitHub repository decocms/studio (401 stars, last pushed today), licensed MIT. It adds 8,900 tokens to every session, about $0.0445 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 2026-08-30.
Other instructions, from other repositories
opengeni AGENTS.md
Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
sixb AGENTS.md
Instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.
hivekeep CLAUDE.md
Instructions for MarlBurroW/hivekeep, covering hivekeep, documentation map, tech stack, key conventions and naming.
useagent CLAUDE.md
Claude Code instructions for useagenthq/useagent, covering useagent - claude.md and hard rules.
agenteval copilot-instructions.md
Instructions for lukasmetzler/agenteval, covering copilot instructions, language, rules and suggestions.
agenteval backend.instructions.md
Instructions for lukasmetzler/agenteval, covering backend instructions, api design, database and performance.