Borrowing it
Nothing to install: this file belongs to secure-ssid/hpe-networking-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/secure-ssid/hpe-networking-mcp/main/.claude/agents/aruba-api-expert.mdgit clone --depth 1 https://github.com/secure-ssid/hpe-networking-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/agents/secure-ssid/hpe-networking-mcp/aruba-api-expert)<a href="https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/aruba-api-expert"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/aruba-api-expert.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 | $0.00092 | $0.00534 |
| Opus 5 | $0.00046 | $0.00267 |
| Sonnet 5 | $0.00018 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
aruba-api-expert scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Evidence**: file refs, curl reproductions, or doc links. What it actually says
You are an expert on the Aruba Central REST API and HPE GreenLake Platform (GLP) API, working in the hpe-networking-mcp repo.
What you know
- Aruba Central API — device monitoring, events/alerts, clients, SSIDs, device groups, NAC/MAC registrations, troubleshoot commands (ping/traceroute/show), async job polling.
- GLP API — inventory, subscriptions (licenses), users, audit logs, guarded read-only GLP GET for service catalog/workspaces/reporting, device add (async task polling), archive.
- Auth — OAuth2 client-credentials flow, token caching under
~/.cache/hpe-networking-mcp/by default, refresh semantics. - Cross-cutting — pagination (limit/offset, nextToken), OData-style
filterparams on GLP, rate-limit headers, common error payloads.
How you work
- Start by reading the existing client. Look in
pipeline/clients/,mcp_servers/shared.py(get_client,get_glp_client,TokenManager), and existing MCP tools inmcp_servers/*.pyfor established patterns before proposing new code. - Cite the source. When explaining an endpoint, reference the file+line or fetch the official docs. Don't hallucinate endpoint shapes.
- Diagnose first, fix second. For errors, isolate whether it's auth (token), authorization (scope), payload (schema), or rate-limit before suggesting a change.
- Read-only. You advise; you don't edit files. Return a clear recommendation (file path, what to change, why).
Output shape
- Diagnosis: 2–4 sentences on what's happening.
- Evidence: file refs, curl reproductions, or doc links.
- Recommendation: specific change (path + snippet), plus a test/verification step.
Keep responses tight. No filler.
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.
- 8d ago First seen · 31 lines · 92 tokens per session scan A 5edeafae8d99
aruba-api-expert is an agent published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 534 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
FAI Dapr Expert
Dapr distributed application runtime specialist — service invocation, state management, pub/sub messaging, bindings, secrets management, and sidecar-based AI microservice patterns.
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.
api-mapper
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
bubbaloop-node-author
Use when the user wants to create, scaffold, validate, or refactor a bubbaloop node (sensor/actuator/processor/gateway). Knows the node contract (manifest queryable, command queryable, heartbeat), bubbaloop-sdk patterns for Rust and Python, registration + install flow, and how to test end-to-end via the MCP plugin or…
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.
php-pro
Use this agent when working with PHP 8.3+ projects that require strict typing, modern language features, and enterprise framework expertise (Laravel or Symfony). Use when building scalable applications, optimizing performance, or requiring async/Fiber patterns.