Borrowing it
Nothing to install: this file belongs to saitoomituru/PSYCHO-Py800MCP. 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/saitoomituru/PSYCHO-Py800MCP/main/AGENTS.mdgit clone --depth 1 https://github.com/saitoomituru/PSYCHO-Py800MCPWrote 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/saitoomituru/psycho-py800mcp/agents-md)<a href="https://agentmods.dev/instructions/saitoomituru/psycho-py800mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/saitoomituru/psycho-py800mcp/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 | $0.02453 | $0.02453 |
| Opus 5 | $0.01226 | $0.01226 |
| Sonnet 5 | $0.00491 | $0.00491 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
PSYCHO-Py800MCP 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 7d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — PSYCHO-Py800MCP エージェント開発指示書
このファイルはAIエージェント(Claude Code等)が本プロジェクトを操作する際の 作法・制約・文脈を定義する。人間が読む設計書は
/docs/を参照。
プロジェクト文脈
PSYCHO-Py800MCPはオシロスコープ・ロジアナ・WebCam・顕微鏡をMCPで統合し、
AIがスケマティックベースで波形を読む、Mac/Win常駐Pythonアプリ。
開発者(齋藤みつる)はZeroRoomLab(山形県高畠町)を拠点とする
コンテンツクリエイター・エンジニア・独立研究者。
実機(SIGLENT SDS1204X-E・Hackintosh)で実際に使うことを前提とした現場駆動開発。
停滞・放置期間が発生することも前提とする。
エージェントはこれを「プロジェクト停止」と判断せず、再開時に /notes/ を確認してから状況を再確認すること。
責任の境界(最重要)
Claude/エージェント → 指揮・提案・コード生成のみ
エッジ端末 → SCPIコマンド実行(ここに責任が宿る)
人間(執行官) → プローブを当てる・Startを押す
エージェントはSCPIコマンドを人間の確認なしに自動実行するコードを書かない。 すべての実機通信は、対象機器、許可操作、上限、TTL、解除条件を持つApprovalSessionの内側で行う。 Phase 0では実験ゲートを閉じ、実機通信を実装・実行しない。query-only実験も別の明示承認後に開始する。
アーキテクチャ概要
src/gui/ - PyQt6常駐アプリ(メニューバー/タスクトレイ)
src/psycho_py800mcp/*_mcp_server.py - FastMCPサーバー(公式`mcp` packageとの名前衝突を避ける)
src/engine/ - ゲシュタルト係数エンジン
src/audio/ - eSpeak NG音声統合
src/evidence/ - 証拠保全(SQLite + HDF5)
docs/ - 仕様書(変更時は必ず更新)
notes/ - 実験ノート・作業ログ(セッション終了時に追記)
詳細は docs/interface_spec.md を参照。
コーディング規約
言語・ライブラリ
- Python 3.11+
- GUI:
PyQt6(システムトレイ・メインウィンドウ) - MCPサーバー:
fastmcp - SCPI通信:
pyvisaorsocket直接(pyvisa-py使用、NI-VISA不要) - 波形処理:
numpy/scipy - 波形保存:
h5py(HDF5) - 証拠ログ:
sqlite3(標準ライブラリ) - 音声:
espeak-ng(CLIラップ orpy-espeak-ng) - スケマティック:
kicad-pythonorskidl
命名規則
# クラス: PascalCase
class GestaltEngine:
# 関数・変数: snake_case
def calculate_coefficient(net_name: str) -> int:
# 定数: UPPER_SNAKE_CASE
MAX_COEFFICIENT = 500
TRIGGER_THRESHOLD = 300
# MCP ツール名: snake_case(動詞_名詞)
def get_waveform_summary(channel: int, duration: float):
def set_trigger(mode: str, level: float):
エラーハンドリング
# ハードウェア応答なし → 必ず明示的に返す
# 「ハードあかん」以上の情報をClaude側に送らない(見えないものは見えない)
return {"status": "error", "message": "device_not_responding", "detail": str(e)}
ゲシュタルト係数エンジン
src/engine/gestalt.py に実装。
COEFFICIENT_WEIGHTS = {
"voltage_unknown": 40,
"gnd_not_isolated": 80,
"voltage_over_50v": 100,
"confidence_low": 60, # confidence < 0.5
"adjacent_net_risk": 30,
"protocol_unanalyzed": 20,
}
THRESHOLDS = {
"normal": (0, 100), # 通常プローブ
"recommend": (100, 300), # 差動プローブ推奨
"required": (300, 400), # 差動プローブ必須+高圧モード
"critical": (400, 500), # 2名体制・監視官承認必須
}
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.
- 7d ago First seen · 228 lines · 2,453 tokens per session scan A 0be528c386b5
PSYCHO-Py800MCP AGENTS.md is an instructions file published in the GitHub repository saitoomituru/PSYCHO-Py800MCP (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,453 tokens to every session, about $0.0123 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
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).
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.
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).
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.