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/claude-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/claude-api-expert)<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>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 | $0.00090 | $0.00492 |
| Opus 5 | $0.00045 | $0.00246 |
| Sonnet 5 | $0.00018 | $0.00098 |
| Haiku 4.5 | $0.00009 | $0.00049 |
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.
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 caching —
cache_controlbreakpoints, 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
- Look at the actual code. Before advising, read the relevant file(s) — don't recommend caching without seeing how the prompt is assembled.
- Be provider-specific. If the code imports
openaior another SDK, flag it and stop — don't force Anthropic patterns onto non-Anthropic code. - Always recommend prompt caching for production agent code. It's the single biggest cost/latency win.
- 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.
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.
- 7d ago First seen · 33 lines · 90 tokens per session scan A 926ea0c81f2d
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.
Other agents, from other repositories
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
timps_log_interpreter
Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
FAI IT Ticket Resolution Tuner
IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.
Demonstrate
Agent for demonstrating VS Code features.