What is gaggiuino-mcp AGENTS.md?

A set of project instructions for a remote server that lets AI assistants interact with a Gaggiuino espresso machine. It describes a TypeScript server, Docker deployment, and a monorepo, which is one repository containing multiple related applications and packages.

Use it when developing or maintaining the ljcl/gaggiuino-mcp server, its interactive shot-graph app, shared interface components, or related packages.

It gives coding agents the architecture and directory context needed to make safe changes in the project.

How ljcl/gaggiuino-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ljcl/gaggiuino-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/ljcl/gaggiuino-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ljcl/gaggiuino-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ljcl/gaggiuino-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ljcl/gaggiuino-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ljcl/gaggiuino-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ljcl/gaggiuino-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ljcl/gaggiuino-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ljcl/gaggiuino-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32,946 This file is loaded in full into every session.

When invoked 32,946 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.32946	$0.32946
Opus 5	$0.16473	$0.16473
Sonnet 5	$0.06589	$0.06589
Haiku 4.5	$0.03295	$0.03295

Measured 8d ago against content hash bcd5061666c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gaggiuino-mcp AGENTS.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(Docker Desktop runs containers in a VM). On a Mac, `curl

AGENTS.md · 2,160 lines

How it starts

The opening of the file, as written. The whole thing — 2,160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gaggiuino MCP Server

Remote MCP server for integrating a Gaggiuino espresso machine with AI tools.

Architecture

Runtime: Bun (TypeScript)
Transport: Streamable HTTP on port 8000 (/mcp endpoint), dual-era — the stateless 2026-07-28 revision and legacy initialize sessions on one endpoint
Deployment: Docker container (any Docker host), exposed via HTTPS tunnel or reverse proxy
Monorepo: Bun workspaces with Turborepo (apps/* + packages/*)

Key Directories

apps/server/ - MCP server (tools, prompts, resources, client)
apps/storybook/ - Standalone Storybook app, serves stories from all packages
packages/shot-graph/ - React + Recharts MCP App for interactive shot graphs
packages/ui/ - Shared MCP app shell: host plumbing (src/host/) plus presentational components (AppShell, ErrorState, ToolbarButton, Legend, Skeleton, Tooltip)
packages/design-system/ - Shared design tokens, components, and host theme presets
packages/vite-config/ - Shared Vite config helpers for MCP Apps
packages/tsconfig/ - Shared TypeScript configurations
apps/server/src/data/profiles.yaml - YAML profile documentation (not machine profiles)
apps/server/src/data/prompts.yaml - System prompt for espresso dial-in guidance
apps/server/src/data/*.example-local.yaml - Templates for user-specific overrides (copy to *.local.yaml)
docs/plans/ - Design docs and implementation plans
docs/upstream/ - Verbatim vendored copies of the Gaggiuino project's own API reference (rest-api.md, websocket.md, MQTT.md), plus the errata that corrects them

The vendored reference, and its errata

docs/upstream/ exists so client.ts can cite a stable path with line numbers that do not move under it. Its README states the posture: these documents settle existence questions, not shape questions — they are hand-written and disagree with themselves about types.

Two rules govern it.

Never edit the vendored files. Their value is that a refresh produces a reviewable diff, and every citation in client.ts is a line reference into them. Corrections go in the README's Errata section, or in client.ts's not-called block when what is being prevented is a bad tool rather than a misreading.
Say where a correction came from. The errata's current entries are drawn from a second, independently written implementation of the same protocols rather than from this repo's hardware, and the README says so at the top of the section. That is strong evidence about behaviour and it is not a specification; where the two disagree, hardware wins.

Read the full file on GitHub · 2,160 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.

8d ago First seen · 2,160 lines · 32,946 tokens per session scan A bcd5061666c6

Subscribe to this mod's changes

gaggiuino-mcp AGENTS.md is an instructions file published in the GitHub repository ljcl/gaggiuino-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 32,946 tokens to every session, about $0.1647 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

gaggiuino-mcp: Instructions file for Codex