Borrowing it
Nothing to install: this file belongs to shigechika/aruba-central-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/aruba-central-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shigechika/aruba-central-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/aruba-central-mcp/claude-md)<a href="https://agentmods.dev/instructions/shigechika/aruba-central-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/aruba-central-mcp/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/shigechika/aruba-central-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/aruba-central-mcp/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 | $0.01110 | $0.01110 |
| Opus 5.5 | $0.00444 | $0.00444 |
| Sonnet 5.5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
aruba-central-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 13d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Overview
MCP server for Aruba Central (GreenLake New Central API, plus optional Classic Central for firmware). Exposes AP, switch, wireless client and firmware status to AI assistants via STDIO transport. Read-only.
Commands
python3 -m venv .venv
.venv/bin/pip install -e ".[test]"
.venv/bin/pytest -v # run all tests
.venv/bin/pytest -v tests/test_client.py # client tests only
.venv/bin/pytest -v tests/test_server.py # server tests only
python3 -m py_compile aruba_central_mcp/client.py # syntax check
Architecture
aruba_central_mcp/client.py—ArubaClient: OAuth2 Client Credentials + httpx + automatic paginationaruba_central_mcp/server.py— MCPServer server with 18 tools (19 with Classic Central configured): AP tools (list_aps, list_radios, list_bssids, list_wlans, list_swarms, get_ap_status, get_ap_throughput, get_top_aps), Client tools (list_clients, find_client_by_mac, get_clients_trend, get_top_clients_by_usage, get_client_mobility_trail), Infrastructure (list_switches, get_site_summary), Firmware (firmware_status, opt-in firmware_versions), plus health_check (server version + backend auth probe) and daily_brief (site-level AP online/offline health summary; buckets APs by siteName, threshold-gated)aruba_central_mcp/classic.py—ClassicClient: Classic Central API gateway, GET-only. The refresh token rotates on every refresh, so the pair lives inARUBA_CLASSIC_TOKEN_FILE; a refresh takes an fcntl lock on<file>.lock, re-reads the file (another process may have refreshed), refuses to refresh when the directory is not writable, and writes the new pair durably (temp + fsync + rename + directory fsync, 0600); a failed write keeps the pair in memory and is reported aspersist_error. The refresh sends secrets as query parameters, so the client sets httpx/httpcore to WARNING and adds a redacting filter; its own logger writes to stderr and does not propagate. Tokens never reach a log line or an error message- Firmware tools:
firmware_status(New Central/network-services/v1/firmware-details+/network-monitoring/v1/aps; with Classic configured, a swarm_id -> group map built from/configuration/v2/groups+/firmware/v1/swarms?group=+ compliance per group, cached 300 s per group in-process (partial reads kept, unread groups first next time), joined to New Central byclusterId==swarm_id-- New Central has no group for AOS-8 APs; the whole call runs under one 48 s deadline passed into every HTTP request) andfirmware_versions(Classic only; registered by_register_optional_tools()only when allARUBA_CLASSIC_*are set, listed inscripts/smoke_probes.OPT_IN_TOOLS). API facts and gaps:docs/firmware-api-notes.md aruba_central_mcp/__main__.py— console-script entry point (aruba-central-mcp, perpyproject.toml);--checkverifies env vars + OAuth2 auth and exits; itsKeyboardInterrupthandler callsos._exit(0)deliberately to bypass normal interpreter shutdown, because MCPServer's stdio reader daemon thread can crash with_enter_buffered_busyon Python 3.14- Environment variables for configuration:
ARUBA_CENTRAL_BASE_URL,ARUBA_CENTRAL_CLIENT_ID,ARUBA_CENTRAL_CLIENT_SECRET; optionalARUBA_CLASSIC_BASE_URL,ARUBA_CLASSIC_CLIENT_ID,ARUBA_CLASSIC_CLIENT_SECRET,ARUBA_CLASSIC_TOKEN_FILE
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.
- 13d ago Changed · +2 lines · +420 tokens per session 67301517f010
- 1mo ago Changed · -2 tokens per session 8a83f6888b86
- 2mo ago First seen · 42 lines · 692 tokens per session scan A 051f9006cea1
aruba-central-mcp CLAUDE.md is an instructions file published in the GitHub repository shigechika/aruba-central-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 1,110 tokens to every session, about $0.0044 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.
aruba-central-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aruba-central-mcp CLAUDE.mdshigechika/aruba-central-mcp | Instructions file | 0 | 11d ago | MIT | A | 1,110 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |