hwprobe-mcp AGENTS.md

hwprobe-mcp AGENTS.md is an instructions file for Codex, OpenCode from notreallycheeks/hwprobe-mcp. It costs 361 tokens per session, scanned A, original, MIT.

Repository instructions for hwprobe-mcp, an MCP server that gives coding agents hardware inventory and live sensor readings. They describe its Python layout, response format, error handling, and local self-test.

In plain words
What is it for?
Use them when modifying hwprobe-mcp, adding hardware collectors, preserving its response conventions, or running the documented self-test.
Why use it?
They give agents consistent rules for extending and checking the server, including how to represent unavailable hardware and collector warnings.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/notreallycheeks/hwprobe-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/notreallycheeks/hwprobe-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.

agentmods badge for hwprobe-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/notreallycheeks/hwprobe-mcp/agents-md.svg)](https://agentmods.dev/instructions/notreallycheeks/hwprobe-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/notreallycheeks/hwprobe-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/notreallycheeks/hwprobe-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 361 This file is loaded in full into every session.
When invoked 361 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00361 $0.00361
Opus 5 $0.00180 $0.00180
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured 3d ago against content hash a4dc3453a273, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hwprobe-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 3d 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.

AGENTS.md · 25 lines

What it actually says

hwprobe-mcp — notes for AI agents working on this repo

What this is

An MCP server (Python, FastMCP) exposing hardware inventory + live sensors to agents. See README.md.

Layout

  • src/hwprobe_mcp/server.py — FastMCP server; each @mcp.tool() is a thin wrapper over aggregate.
  • src/hwprobe_mcp/aggregate.py — composes collectors into the 6 tool responses.
  • src/hwprobe_mcp/collectors/ — one module per backend; each is independent and degrades gracefully.
  • src/hwprobe_mcp/util.pyrun() / run_json() (never raise), platform flags, envelope().
  • src/hwprobe_mcp/__main__.py--selftest (dumps all collector JSON), --version, else runs the server.

Conventions

  • Collectors never raise. Catch everything; append a string to the warns list passed in.
  • Every tool returns the envelope(sources, data, warnings, ok) shape — keep it consistent.
  • A missing binary, absent device, or permission error is a warnings[] entry, not an error.
  • Numbers stay numbers (parse CSV/JSON to int/float); unavailable values become null, not "N/A".

Verify locally

PYTHONPATH=src python -m hwprobe_mcp --selftest | jq .   # no `mcp` dep needed for selftest
pytest                                                    # smoke tests

Full sensor/inventory/SMART data needs root; unprivileged runs are expected to show warnings.

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.

  1. 3d ago First seen · 25 lines · 361 tokens per session scan A a4dc3453a273

Subscribe to this mod's changes

hwprobe-mcp AGENTS.md is an instructions file published in the GitHub repository notreallycheeks/hwprobe-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 361 tokens to every session, about $0.0018 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.

Related

Other instructions, from other repositories