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/roostercoopllc/flipper-mcp/agents-mdgit clone --depth 1 https://github.com/roostercoopllc/flipper-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/roostercoopllc/flipper-mcp/agents-md)<a href="https://agentmods.dev/instructions/roostercoopllc/flipper-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/roostercoopllc/flipper-mcp/agents-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 | $0.04729 | $0.04729 |
| Opus 5 | $0.02364 | $0.02364 |
| Sonnet 5 | $0.00946 | $0.00946 |
| Haiku 4.5 | $0.00473 | $0.00473 |
Grade C, and why
flipper-mcp AGENTS.md scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Flipper MCP Server
This file provides all context an AI agent (or human developer) needs to pick up this project and continue implementation from any machine.
1. Project Overview
flipper-mcp is a Rust-based MCP (Model Context Protocol) server that runs directly on the Flipper Zero's WiFi Dev Board v1 (ESP32-S2). It exposes all default Flipper Zero applications as MCP tools over HTTP, allowing AI agents (Claude, etc.) to programmatically control a Flipper Zero over the network.
This is distinct from existing projects (e.g., busse/flipperzero-mcp) which run on a host computer. This server runs on the hardware itself.
Repo: https://github.com/roostercoopllc/flipper-mcp
2. Architecture
LOCAL ACCESS:
┌─ Local Network ─────────────────────────────────────────┐
│ │
│ Claude/MCP Client ──HTTP──► flipper-mcp.local:8080 │
│ (ESP32-S2 WiFi Board) │
│ │ │
│ UART │
│ │ │
│ Flipper Zero │
│ (STM32WB55) │
└─────────────────────────────────────────────────────────┘
REMOTE ACCESS:
Claude/MCP Client ──HTTP──► Relay Server ◄──WebSocket── ESP32-S2 ──UART──► Flipper Zero
(any machine) (outbound) (WiFi Board) (main MCU)
Data flow: MCP JSON-RPC requests arrive over HTTP at the ESP32-S2. The firmware translates them into Flipper Zero CLI commands sent over UART at 115200 baud. Responses are parsed and returned as structured JSON.
Remote access: The ESP32-S2 initiates an outbound WebSocket connection to a relay server. The relay accepts MCP HTTP requests from clients and forwards them through the WebSocket tunnel. This solves NAT traversal and unknown-IP scenarios.
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.
- 6d ago First seen · 449 lines · 4,729 tokens per session scan C 087829203685
flipper-mcp AGENTS.md is an instructions file published in the GitHub repository roostercoopllc/flipper-mcp (16 stars, last pushed 6mo ago), licensed MIT. It adds 4,729 tokens to every session, about $0.0236 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.