Borrowing it
Nothing to install: this file belongs to notreallycheeks/hwprobe-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.
curl -O https://raw.githubusercontent.com/notreallycheeks/hwprobe-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/notreallycheeks/hwprobe-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/notreallycheeks/hwprobe-mcp/agents-md)<a href="https://agentmods.dev/instructions/notreallycheeks/hwprobe-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/notreallycheeks/hwprobe-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.
<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="Reviewed on agentmods" width="80" 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 | $0.00361 | $0.00361 |
| Opus 5.5 | $0.00144 | $0.00144 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
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 2mo 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.
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 overaggregate.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.py—run()/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
warnslist 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.
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.
- 2mo ago First seen · 25 lines · 361 tokens per session scan A a4dc3453a273
hwprobe-mcp AGENTS.md is an instructions file published in the GitHub repository notreallycheeks/hwprobe-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 361 tokens to every session, about $0.0014 per session on Opus 5.5. 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.
hwprobe-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hwprobe-mcp AGENTS.mdnotreallycheeks/hwprobe-mcp | Instructions file | 0 | 4d ago | MIT | A | 361 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 1,907 | GitHub Copilot |