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/sandraschi/devices-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/devices-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/sandraschi/devices-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/devices-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/devices-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 | $0.01198 | $0.01198 |
| Opus 5 | $0.00599 | $0.00599 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
devices-mcp 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 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devices-mcp — Per-Repo Agent Instructions
Last updated: 2026-06-02
Fleet standard: D:\Dev\repos\mcp-central-docs\standards\AGENTS.md
Version: v1.21.5 (beta)
Default git branch: main — ignore master (legacy mirror; may be deleted)
What this repo is
Beta home IoT stack — three delivery legs, one Python package:
| Leg | Path / artifact | Role |
|---|---|---|
| 1 — MCP | src/devices_mcp/server_v2.py, devices-mcp.mcpb |
FastMCP stdio/HTTP, portmanteau tools |
| 2 — Webapp | web-sota/ |
FastAPI :10717 + React SPA /app/ |
| 3 — Desktop | native/ → NSIS installer |
Tauri + PyInstaller sidecars |
Rule: Only one backend on 10717. NSSM service and Tauri must not both bind the port.
Docs hub: docs/README.md · architecture: docs/ARCHITECTURE.md
Git branches
main— sole development and release branch; GitHub default.master— leftover from pre-rename / old CI; was ahead of nothing useful. Do not branch from it. If it diverges again, fast-forward or delete on GitHub.
Clone: git clone https://github.com/sandraschi/devices-mcp then git checkout main if needed.
Startup
# Backend only (FastAPI, port 10717)
Set-Location D:\Dev\repos\devices-mcp\web-sota
$env:PYTHONPATH = "D:\Dev\repos\devices-mcp\src;D:\Dev\repos\devices-mcp\web-sota"
uv run python -m backend.server --host 127.0.0.1 --port 10717
# Full webapp (backend + Vite HMR on 10716)
D:\Dev\repos\devices-mcp\web-sota\start.ps1
# http://127.0.0.1:10717/app/
# MCP stdio
Set-Location D:\Dev\repos\devices-mcp
uv run python -m devices_mcp.server_v2
# Regenerate LLM index files
uv run python -m devices_mcp.utils.llms_txt
Packaged backend: run_webapp_backend.py (PyInstaller sidecar).
Ports
| Port | Service |
|---|---|
| 10717 | FastAPI backend + static SPA |
| 10716 | Vite dev frontend only |
| 10715 | USB / camera helper sidecar (optional) |
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 · 120 lines · 1,198 tokens per session scan A 69a3f8db9f4f
devices-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/devices-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 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
fastmcp CLAUDE.md
Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.
core integrations.instructions.md
Instructions for home-assistant/core, covering file locations, general guidelines, entity platforms, integration quality scale and how rules apply.
Gladys AGENTS.md
AGENTS.md instructions for GladysAssistant/Gladys, covering agents.md, cursor cloud specific instructions, running the app (dev mode), non-obvious caveats and feature specs (spec-first process).
core copilot-instructions.md
Copilot instructions for home-assistant/core, covering copilot code review instructions, pull request template, breaking change, proposed change and type of change.
mcp-arr AGENTS.md
Instructions for aplaceforallmystuff/mcp-arr, covering agents.md - mcp-arr, tech stack, architecture, development commands and build.
unraid CLAUDE.md
Claude Code instructions for dinglebear-ai/unraid, covering claude.md, what this is, identity and history (read before touching any url), "unraid-mcp" means five different things and agent plugins ship no claude code hooks.