Borrowing it
Nothing to install: this file belongs to workfloworchestrator/junos-mcp-server. 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/workfloworchestrator/junos-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/workfloworchestrator/junos-mcp-serverWrote 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/workfloworchestrator/junos-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/workfloworchestrator/junos-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/workfloworchestrator/junos-mcp-server/claude-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/workfloworchestrator/junos-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/workfloworchestrator/junos-mcp-server/claude-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 | $0.00426 | $0.00426 |
| Opus 5.5 | $0.00170 | $0.00170 |
| Sonnet 5.5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
junos-mcp-server 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 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
CLAUDE.md
Read-only JUNOS troubleshooting MCP server.
Invariant (do not break)
Read-only only. NEVER add a configuration/write tool. Every device command goes
through validate_show_command(), which allows only show commands and blocks
| save / | append / | tee / | load.
Layout
src/junos_mcp_server/server.py— the whole server:Settings(pydantic-settingsBaseSettings, env vars viavalidation_alias) +settings(),fetch_targets()(cached), theShowCommandpydantic model +validate_show_command(),run_show()(PyEZ), and FastMCP toolslist_devices/run_show_command.tests/test_server.py— parametrized unit tests for the command validator, target parsing, and tool dispatch. (Settings is plain pydantic — not retested.)
Targets source
GET {ORCHESTRATOR_URL}/api/surf/subscriptions/gnmi/targets (Basic Auth). The
address field is fqdn:32767 (gNMI port) — we use the FQDN only and connect
NETCONF on JUNOS_SSH_PORT (830).
Dev mode: JUNOS_DEV_MODE=1 + JUNOS_DEV_TARGETS (JSON list of node hostnames)
makes fetch_targets() return {node: node} and skip the orchestrator. A
model_validator enforces the mode rules: dev needs non-empty JUNOS_DEV_TARGETS;
prod needs ORCHESTRATOR_URL + GNMIC_HTTP_BASIC_*. SSH creds required in both.
Test
uv run --extra dev pytest -v
Style
Prefer comprehensions / itertools / next(..., None) over imperative loops,
break, continue. Use @pytest.mark.parametrize for data-varying tests.
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 · 35 lines · 426 tokens per session scan A e58a4601705a
junos-mcp-server CLAUDE.md is an instructions file published in the GitHub repository workfloworchestrator/junos-mcp-server (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 426 tokens to every session, about $0.0017 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.
junos-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| junos-mcp-server CLAUDE.mdworkfloworchestrator/junos-mcp-server | Instructions file | 0 | 23d ago | Apache-2.0 | A | 426 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |