A guided setup for building voice or chat agents with ElevenLabs, a service for creating conversational audio and text applications.

Use it to scaffold a voice agent, phone bot, chat agent, or customer-support interface in Python, React, or JavaScript.

It helps choose an agent type and programming stack before code is generated, while checking current ElevenLabs documentation for API details.

build-agent — Skill for Claude Code by kenrogers

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.

Any agent

npx skills add kenrogers/elevenlabs-claude-plugin --skill build-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kenrogers/elevenlabs-claude-plugin/build-agent/github.svg)](https://agentmods.dev/skills/kenrogers/elevenlabs-claude-plugin/build-agent)

Your own site

<a href="https://agentmods.dev/skills/kenrogers/elevenlabs-claude-plugin/build-agent"><img src="https://agentmods.dev/badge/skills/kenrogers/elevenlabs-claude-plugin/build-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kenrogers/elevenlabs-claude-plugin/build-agent"><img src="https://agentmods.dev/badge/skills/kenrogers/elevenlabs-claude-plugin/build-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 620 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00620
Opus 5	$0.00034	$0.00310
Sonnet 5	$0.00013	$0.00124
Haiku 4.5	$0.00007	$0.00062

Measured 9d ago against content hash 0e62d09e1b37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

build-agent 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.

skills/build-agent/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build a Voice Agent

Before generating any code:

Identify the relevant Conversational AI doc URLs from the knowledge file at .claude/elevenlabs/knowledge/general-elevenlabs-knowledge.md
Fetch the current docs for the Conversational AI section:
- Python SDK: https://elevenlabs.io/docs/eleven-agents/libraries/python.mdx
- React SDK: https://elevenlabs.io/docs/eleven-agents/libraries/react.mdx
- JavaScript SDK: https://elevenlabs.io/docs/eleven-agents/libraries/java-script.mdx
Use the fetched content as the source of truth for API parameters and patterns
If fetch fails, fall back to the static knowledge base BUT warn: "Generated code is based on cached knowledge and may not reflect the latest SDK. Run /elevenlabs:update-docs to refresh."

Steps:

Ask the user what type of agent they want to build using AskUserQuestion:
- Voice Agent — Real-time voice conversation (phone/web)
- Chat Agent — Text-based conversational agent
- Phone Bot — Inbound/outbound phone calls
Ask the user about their tech stack:
- Python — Backend voice agent with Python SDK
- React — Browser-based voice agent with React SDK
- Node.js/JavaScript — Server-side or vanilla JS client
Ask what tools/capabilities the agent needs:
- Example: "Book appointments", "Look up orders", "Transfer to human"
- These become ClientTools registrations

Generate the project structure:

voice-agent/
├── src/
│   ├── agent.py (or agent.ts)     # Main agent setup
│   └── tools.py (or tools.ts)     # ClientTools implementations
├── .env.example                    # ELEVENLABS_API_KEY, ELEVENLABS_AGENT_ID
├── requirements.txt (or package.json)
└── README.md                       # Setup and run instructions

Generate code with:
- Correct Conversation initialization (with ALL required kwargs: requires_auth, audio_interface)
- ClientTools setup with proper async handling
- Audio interface configuration
- Environment variable management
- Error handling and graceful shutdown
- README with setup instructions

Read the full file on GitHub · 53 lines

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.

9d ago First seen · 53 lines · 67 tokens per session scan A 0e62d09e1b37

Subscribe to this mod's changes

build-agent is a skill published in the GitHub repository kenrogers/elevenlabs-claude-plugin (3 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 620 once invoked, about $0.0003 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens