Borrowing it
Nothing to install: this file belongs to zinntikumugai/rigol-oscilloscope-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/zinntikumugai/rigol-oscilloscope-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/zinntikumugai/rigol-oscilloscope-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/zinntikumugai/rigol-oscilloscope-mcp/agents-md)<a href="https://agentmods.dev/instructions/zinntikumugai/rigol-oscilloscope-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zinntikumugai/rigol-oscilloscope-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/zinntikumugai/rigol-oscilloscope-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zinntikumugai/rigol-oscilloscope-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 | $0.01733 | $0.01733 |
| Opus 5 | $0.00866 | $0.00866 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
rigol-oscilloscope-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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — エージェント向け開発ガイド
Rigol製オシロスコープをSCPI経由で操作するMCPサーバー(Python)。要件・仕様の規範は docs/README.md から辿ること(Requirements / tools / device-profiles / verification / roadmap)。
コマンド
mise install # Python + uv(バージョンはmise管理、依存はuv管理)
uv sync # 依存解決(dev含む)
uv run pytest # ユニットテスト全件(実機不要、FakeScopeで完結)
uv run pytest tests/test_xxx.py -v # 単一ファイル
RIGOL_MCP_FAKE=1 uv run rigol-oscilloscope-mcp # 実機なしでstdio起動(FakeScope接続)
# 実機テスト(env-gated。未設定なら自動skip)
RIGOL_TEST_ADDRESS=<実機IP> uv run pytest -m device # read-only
RIGOL_TEST_ADDRESS=<実機IP> RIGOL_TEST_ALLOW_WRITE=1 uv run pytest -m device_write # write(復元付き)
mise外のシェルでは mise exec -- uv run ... を使う。
アーキテクチャ
server.py(FastMCP、38 Tool、同期def+lock直列化)
→ service/(connection / state / measurement / waveform / analysis / screenshot / control / decode / paths)
→ safety/(操作クラス表 / confirmトークン / 監査ログJSONL)
→ driver/(session: drain・set_and_verify / scope: プロファイル対応SCPI生成 / decode: :BUS変換表)
→ transport/(lan: raw socket 5555 / usb: PyVISA / blocks: IEEE488.2ブロック)
profiles/(YAML機種プロファイル: verified→family→guide→generic の解決順。guide=ガイド逐語解読のみ・実機未検証)
testing/(FakeScope: MHO98方言のフェイク機器。Transport層に差し込む)
skills/ + .claude-plugin/ + .codex-plugin/ + .agents/(Claude/Codex両プラグイン: 共有スキル+ホスト別マニフェスト。tests/test_plugin.py が整合を検証)
- MCP SDKのimportは
server.pyに閉じ込める。Toolは全て同期defで、返却は baredict注釈(structured content回避、実測済みの仕様) - エラーは例外でなく
{"error": true, "code": ..., "message": ..., "detail": ...}のJSONを正常contentで返す(デコレータが変換)
絶対に守るルール
- 実機のIPアドレス・シリアルをリポジトリ内のいかなるファイルにも書かない。 実機は
RIGOL_TEST_ADDRESS環境変数でのみ渡す。tests/test_ip_guard.pyがlintしており、コミット前にgit grep "172\.16\."が空であることを確認する。例示IPが必要なら TEST-NET(192.0.2.x)を使う - プロファイルで確認されていないSCPIニモニックを実機に送らない。 実機MHO98は未定義ヘッダのクエリ1発でSCPIサーバー全体が沈黙する(再接続でも回復せず、空行1本で回復 —
LanTransport.open()が対策済み)。未対応機能は送信前にUNSUPPORTED_FEATUREを返す。新しいコマンドは機種プロファイル(profiles/data/*.yaml)への宣言とセットで追加する。*OPT?はRigolオシロ全シリーズで未定義ヘッダ(ガイド確認済み)。オプション照会は:SYSTem:OPTion:STATus?+ガイド記載トークンのみを使う(リスト外トークンでも沈黙する) - 設定系は set → エラーキュー確認 → read-back を必須とし、requested / applied の両値を返す(機器は1-2-5にスナップしない。yorigin等のプリアンブル値は動的なので必ずライブ値を使う)
- 実機で実行禁止: 50Ω設定(FIFT)、autoset、factory reset(confirmフローはFakeScopeテストのみで担保)。実機writeテストは必ず「現在値取得→set→readback→finallyで復元」パターン
- 新Toolの追加手順:
safety/classes.pyのTOOL_CLASSESへ分類を追記(未登録は起動失敗する)。RESTRICTED_WRITE / DANGEROUS_WRITE に分類したらconfirm_token引数が必須(起動時チェックが強制)。引数条件付きの昇格(configure_channelの50Ω等)はservice/control.pyの責務
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.
- 10d ago First seen · 60 lines · 1,733 tokens per session scan A d6da19218428
rigol-oscilloscope-mcp AGENTS.md is an instructions file published in the GitHub repository zinntikumugai/rigol-oscilloscope-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 1,733 tokens to every session, about $0.0087 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
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).