Borrowing it
Nothing to install: this file belongs to shigechika/junos-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/shigechika/junos-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shigechika/junos-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/shigechika/junos-mcp/claude-md)<a href="https://agentmods.dev/instructions/shigechika/junos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/junos-mcp/claude-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 | $0.03668 | $0.03668 |
| Opus 5 | $0.01834 | $0.01834 |
| Sonnet 5 | $0.00734 | $0.00734 |
| Haiku 4.5 | $0.00367 | $0.00367 |
Grade A, and why
junos-mcp CLAUDE.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 5d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
このファイルはClaude Codeがリポジトリを理解するためのコンテキストを提供します。
プロジェクト概要
junos-mcpは、junos-ops の機能を MCP (Model Context Protocol) サーバーとして公開するパッケージです。Claude Desktop、Claude Code などの MCP 対応 AI アシスタントから Juniper Networks デバイスの操作が可能になります。
- junos-ops: CLI ツール + ライブラリ(人間が直接使う)
- junos-mcp: junos-ops を MCP サーバーとして公開(AI アシスタントが使う)
技術スタック
- 言語: Python 3(3.12以上)
- 主要ライブラリ: MCP Python SDK(FastMCP)、junos-ops(junos-eznc)
- トランスポート: STDIO(デフォルト)または Streamable HTTP(
--transportで選択、JSON-RPC) - パッケージ管理: pyproject.toml(pip installable)
- テスト: pytest + モック
- ライセンス: Apache License 2.0
ファイル構成
junos_mcp/
├── __init__.py # パッケージ定義、__version__
├── __main__.py # python -m junos_mcp 対応
├── pool.py # per-host NETCONF 接続プール(ConnectionPool、get_pool)
└── server.py # FastMCP サーバー定義、24ツール実装
tests/
├── __init__.py
├── test_pool.py # 27 ユニットテスト(ConnectionPool)
├── test_server.py # 128 ユニットテスト
└── test_version_consistency.py # 2 ユニットテスト(バージョン整合性)
pyproject.toml # パッケージメタデータ、依存関係
LICENSE # Apache License 2.0
README.md # 英語版
README.ja.md # 日本語版
モジュール構成
pool.py — 接続プール
ConnectionPool— per-host NETCONF 接続プール。acquire(hostname, config_path)context manager で checkout/checkin。per-hostthreading.Lockを操作全体で保持し PyEZDeviceのスレッドセーフ問題を回避。アイドルタイムアウト超過・dev.connected==Falseで自動退場・再接続。PoolConnectionError— 接続失敗時にacquire()が raise する例外。get_pool()— モジュールレベルシングルトンを lazy init して返す。JUNOS_MCP_POOL=0でNoneを返す(プール無効)。- 環境変数:
JUNOS_MCP_POOL(無効化)・JUNOS_MCP_POOL_IDLE(アイドルタイムアウト秒、デフォルト 60)・JUNOS_MCP_POOL_CONNECT_ATTEMPTS(一過性接続失敗のリトライ回数、デフォルト 2=1 回リトライ)・JUNOS_MCP_POOL_CONNECT_DELAY(リトライ間隔秒、デフォルト 1.0) - 接続リトライの不変条件(PR #37): リトライ対象は
_RETRYABLE_CONNECT_ERRORS(ConnectError/ConnectTimeoutErrorのみ)に限定。ConnectAuthError(認証失敗)は意図的に除外 — 誤った資格情報でリトライするとアカウントロックの恐れがあるため即座に fail-fast する。リトライの sleep は per-hostentry.lockを保持したまま実行する(設計どおり — 同一ホストの呼び出しのみをブロックし他ホストは妨げない)
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.
- 5d ago First seen · 177 lines · 3,668 tokens per session scan A 00b4e3eb186c
junos-mcp CLAUDE.md is an instructions file published in the GitHub repository shigechika/junos-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,668 tokens to every session, about $0.0183 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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).
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).
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.