junos-mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

junos-mcp copilot-instructions.md is an instructions file for GitHub Copilot from shigechika/junos-mcp. It costs 2,585 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for working on junos-mcp, an MCP server that gives AI assistants access to Juniper JUNOS devices. It documents the project structure, build and test commands, and review concerns such as keeping standard output reserved for protocol messages.

In plain words
What is it for?
Use it when building, testing, or reviewing changes to the junos-mcp Python server. It is especially relevant for changes to the server and connection-pool code.
Why use it?
It gives a coding assistant the project context needed to make and review changes safely. It also explains details that may otherwise cause misleading review comments, such as version values used as sentinels and counts that can become outdated.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions CLAUDE.md.

This is shigechika/junos-mcp's own configuration. It tells GitHub Copilot how to work on junos-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything junos-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/shigechika/junos-mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/shigechika/junos-mcp

Made for: GitHub Copilot.

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 junos-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shigechika/junos-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/shigechika/junos-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/shigechika/junos-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/junos-mcp/copilot-instructions/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.

agentmods 80×15 button for junos-mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shigechika/junos-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shigechika/junos-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,585 This file is loaded in full into every session.
When invoked 2,585 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02585 $0.02585
Opus 5.5 $0.01034 $0.01034
Sonnet 5.5 $0.00517 $0.00517
Haiku 4.5 $0.00259 $0.00259

Measured 1mo ago against content hash eec5ee47d900, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

junos-mcp copilot-instructions.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 1mo 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.

.github/copilot-instructions.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository overview

junos-mcp is an MCP (Model Context Protocol) server that exposes junos-ops (a Juniper JUNOS CLI tool/library) to AI assistants over stdio (default) or streamable-http transport. Built on the official mcp Python SDK's MCPServer (junos_mcp/server.py; the dependency is mcp>=2,<3), with per-host NETCONF connection pooling in junos_mcp/pool.py.

See CLAUDE.md (Japanese) for the authoritative module/tool inventory and design notes — read it before reviewing changes to server.py or pool.py. Its tool/test counts have drifted upward before as tools were added, so don't treat those numbers in CLAUDE.md as exact — check grep -c '^@mcp.tool' junos_mcp/server.py and the test run output instead of citing a possibly-stale figure in review comments.

Build & validate

python3 -m venv .venv
. .venv/bin/activate
pip install -e ".[test]"
pytest tests/ -v

This mirrors .github/workflows/test.yml (matrix over Python 3.12–3.14 on Linux, plus one Windows 3.12 job specifically to guard against stdio newline regressions, modelcontextprotocol/python-sdk#2433), plus a lint job running ruff check . at a pinned version. ruff format is deliberately not gated (see ruff.toml) and there is no black/mypy job — don't hold diffs to a formatting or typing standard this repo hasn't opted into, and don't restate what ruff check already enforces.

What to focus review on in this repo

1. stdio transport: stdout is the JSON-RPC channel

server.py's module docstring documents the actual mechanism: junos-ops core functions (≥0.16.9) return structured dicts and never print; MCP tools render text via junos_ops.display.format_*(result), which return a string rather than printing one. No contextlib.redirect_stdout exists anywhere in the module — it isn't needed because nothing on this path calls print(). Flag any new tool code in server.py that calls print(), writes to stdout directly, or lets a dependency's default logging fall through to stdout.

Read the full file on GitHub · 181 lines

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. 1mo ago Changed · +9 tokens per session eec5ee47d900
  2. 2mo ago First seen · 181 lines · 2,576 tokens per session scan A 721ebde78f25

Subscribe to this mod's changes

junos-mcp copilot-instructions.md is an instructions file published in the GitHub repository shigechika/junos-mcp (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 2,585 tokens to every session, about $0.0103 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.

Related

junos-mcp copilot-instructions.md compared with instructions from other repositories

junos-mcp copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
junos-mcp copilot-instructions.mdshigechika/junos-mcpInstructions file111d agoApache-2.0A2,585GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode