expert-advice

expert-advice is a command for Claude Code from kenrogers/elevenlabs-claude-plugin. It costs 35 tokens per session (505 once invoked), scanned A, original, MIT.

A review command for projects that use ElevenLabs, a service for generating or handling speech and voice agents. It checks Python and JavaScript or TypeScript code against current ElevenLabs guidance and known problem patterns.

In plain words
What is it for?
Reviewing ElevenLabs SDK usage, streaming and model choices, API-key handling, retry behavior, voice-agent sessions, WebSockets, and client tools.
Why use it?
It helps find outdated or risky patterns in voice-agent code, including authentication mistakes, weak error handling, and incorrect session or audio cleanup.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the elevenlabs plugin — 4 skills, 4 commands, 3 hooks shipped together

Good fit Reviewing ElevenLabs SDK usage, streaming and model choices, API-key handling, retry behavior, voice-agent sessions, WebSockets, and client tools.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kenrogers/elevenlabs-claude-plugin/expert-advice
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/kenrogers/elevenlabs-claude-plugin

Made for: Claude Code.

Or install elevenlabs, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 3 hooks.

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 expert-advice

README.md
[![agentmods](https://agentmods.dev/badge/commands/kenrogers/elevenlabs-claude-plugin/expert-advice/github.svg)](https://agentmods.dev/commands/kenrogers/elevenlabs-claude-plugin/expert-advice)
Your own site
<a href="https://agentmods.dev/commands/kenrogers/elevenlabs-claude-plugin/expert-advice"><img src="https://agentmods.dev/badge/commands/kenrogers/elevenlabs-claude-plugin/expert-advice/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.

agentmods 80×15 button for expert-advice

Your own site · 80×15
<a href="https://agentmods.dev/commands/kenrogers/elevenlabs-claude-plugin/expert-advice"><img src="https://agentmods.dev/badge/commands/kenrogers/elevenlabs-claude-plugin/expert-advice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00035 $0.00505
Opus 5 $0.00017 $0.00253
Sonnet 5 $0.00007 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 9d ago against content hash 4dd8441e3026, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

expert-advice 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 9d 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.

commands/expert-advice.md · 26 lines

What it actually says

  1. Find all Python and TypeScript/JavaScript files in the project that use the ElevenLabs SDK (search for imports of elevenlabs, @11labs/react, @11labs/client, or references to ELEVENLABS_API_KEY)
  2. Fetch the latest docs from elevenlabs.io/docs/llms.txt for current reference. If fetch fails, fall back to the knowledge base at .claude/elevenlabs/knowledge/general-elevenlabs-knowledge.md but warn the user that the review is based on potentially stale patterns.
  3. Read the anti-patterns block from .claude/elevenlabs/knowledge/general-elevenlabs-knowledge.md (between <!-- HOOK_PATTERNS_START --> and <!-- HOOK_PATTERNS_END --> markers) for machine-readable pattern checks
  4. Review all ElevenLabs code against this checklist:
    • API usage patterns — streaming vs batch, correct endpoints, proper model selection
    • Authentication & key management — env vars, no client-side exposure, proper token usage
    • Error handling & retry logic — ApiError handling, 429 backoff, timeout handling
    • Voice agent lifecycle — proper session start/end, audio interface cleanup, WebSocket management
    • ClientTools registration — async handling, proper parameter extraction, error returns
    • Audio format & quality — correct model for use case, output format settings
    • Rate limiting awareness — backoff strategy, request queuing for high-volume usage
  5. Generate a structured report organized by severity:
    • 🔴 Critical — Security issues, missing required params, will crash at runtime
    • 🟠 High — Incorrect patterns that will cause bugs or poor UX
    • 🟡 Medium — Suboptimal patterns, performance issues
    • 🟢 Low — Style suggestions, minor improvements
  6. Offer to apply fixes — if the user agrees, use the Edit tool to apply changes directly
  7. After fixes, suggest /elevenlabs:test-agent if voice agent code was reviewed

User's request: $ARGUMENTS

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. 9d ago First seen · 26 lines · 35 tokens per session scan A 4dd8441e3026

Subscribe to this mod's changes

expert-advice is a command published in the GitHub repository kenrogers/elevenlabs-claude-plugin (3 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 505 once invoked, about $0.0002 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.