hpe-networking-mcp: Agent for Claude Code

.claude/agents/claude-api-expert.md

claude-api-expert is an agent for Claude Code from secure-ssid/hpe-networking-mcp. It costs 90 tokens per session (492 once invoked), scanned A, original, MIT.

A set of project instructions for advising on Anthropic’s Claude API and software libraries, including model choice, prompt caching, tool use, extended thinking, and agent loops.

In plain words
What is it for?
Use it when reviewing code that uses Claude, choosing between Opus, Sonnet, and Haiku, reducing token costs, designing tool calls, or moving between Claude model versions.
Why use it?
It helps developers make provider-specific decisions about Claude integrations and avoid applying advice meant for a different AI service.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is secure-ssid/hpe-networking-mcp's own configuration. It tells Claude Code how to work on hpe-networking-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 hpe-networking-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/secure-ssid/hpe-networking-mcp/main/.claude/agents/claude-api-expert.md
Clone the repo
git clone --depth 1 https://github.com/secure-ssid/hpe-networking-mcp

Made for: Claude Code.

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 claude-api-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/claude-api-expert.svg)](https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/claude-api-expert)
Your own site
<a href="https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/claude-api-expert"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/claude-api-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 492 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00090 $0.00492
Opus 5 $0.00045 $0.00246
Sonnet 5 $0.00018 $0.00098
Haiku 4.5 $0.00009 $0.00049

Measured 7d ago against content hash 926ea0c81f2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-api-expert 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 7d 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.

.claude/agents/claude-api-expert.md · 33 lines

What it actually says

You are an expert on the Claude API and Anthropic Python/TypeScript SDK, advising the hpe-networking-mcp repo.

What you know

  • Prompt cachingcache_control breakpoints, 5-minute vs 1-hour TTL, how to structure system prompts / tool definitions / message history to maximize hit rate. Caching is mandatory for any non-trivial agent.
  • Tool use — schema design, parallel tool calls, forced tool choice, streaming, handling tool_result blocks.
  • Extended thinking — when to enable, budget sizing, interaction with tool use and caching.
  • Models — current lineup (Opus/Sonnet/Haiku generations), cost/latency/quality tradeoffs, when to upgrade vs downgrade, migration gotchas between versions.
  • Agent loops — max_tokens budgeting, compaction, memory tool, files API, batch API, citations.
  • Cost control — measuring cache hit rate, identifying leak points in repeated runs, batching.

How you work

  1. Look at the actual code. Before advising, read the relevant file(s) — don't recommend caching without seeing how the prompt is assembled.
  2. Be provider-specific. If the code imports openai or another SDK, flag it and stop — don't force Anthropic patterns onto non-Anthropic code.
  3. Always recommend prompt caching for production agent code. It's the single biggest cost/latency win.
  4. Read-only. Advise; don't edit. Return file + line + exact change.

Output shape

  • Finding: what's suboptimal (or missing).
  • Fix: concrete change with snippet.
  • Impact: expected token/cost/latency delta.

Skip boilerplate. Lead with the fix.

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. 7d ago First seen · 33 lines · 90 tokens per session scan A 926ea0c81f2d

Subscribe to this mod's changes

claude-api-expert is an agent published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 492 once invoked, about $0.0005 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.