setup

setup is a command for coding agents from PatterAI/awesome-claude-call. It costs 11 tokens per session (1,275 once invoked), scanned B, original, MIT.

A setup wizard for connecting a Twilio phone account to a voice service and an OpenAI API key. Twilio provides phone calling, while the voice service handles spoken conversation.

In plain words
What is it for?
Use it to enter credentials manually or import them from a .env file, a text file commonly used for configuration values.
Why use it?
It gathers and saves the credentials needed to make or receive calls through the voice agent.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-call plugin — 9 commands, 1 agent, 4 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/patterai/awesome-claude-call/setup
Clone the repo
git clone --depth 1 https://github.com/PatterAI/awesome-claude-call

Or install claude-call, the plugin that ships this one along with the rest of its 9 commands, 1 agent, 4 hooks, 1 MCP server.

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/patterai/awesome-claude-call/setup.svg)](https://agentmods.dev/commands/patterai/awesome-claude-call/setup)
Your own site
<a href="https://agentmods.dev/commands/patterai/awesome-claude-call/setup"><img src="https://agentmods.dev/badge/commands/patterai/awesome-claude-call/setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,275 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00011 $0.01275
Opus 5 $0.00005 $0.00638
Sonnet 5 $0.00002 $0.00255
Haiku 4.5 $0.00001 $0.00128

Measured 4d ago against content hash ef1d838a32c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 0600 "$HOME/.claude-call/credentials"
commands/setup.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/claude-call:setup

You are running the claude-call setup wizard. Walk the user through configuring credentials.

Minimum requirements: Twilio account (SID, auth token, phone number) + OpenAI API key. Optional alternatives: ElevenLabs ConvAI, or pipeline mode (Deepgram STT + ElevenLabs TTS + OpenAI LLM).

Step 1 — Check existing config

test -s "$HOME/.claude-call/credentials" && echo EXISTS || echo MISSING

If EXISTS, ask the user with AskUserQuestion: "Existing credentials found at ~/.claude-call/credentials. Overwrite?" (Yes / No). If No, exit with the message "Setup cancelled. Existing credentials kept."

Step 1.5 — Choose credential source

Use AskUserQuestion: "How do you want to provide credentials?"

  • Enter manually — Walk through Twilio + voice-engine prompts.
  • Import from a .env file — Skip the prompts; read keys from a path you give me.

If the user picks Import from .env, ask AskUserQuestion for the absolute path. Read it with the Read tool. Extract these keys (case-sensitive, last value wins):

  • TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, TWILIO_PHONE_NUMBER (required)
  • OPENAI_API_KEY (required for the default engine)
  • ELEVENLABS_API_KEY, ELEVENLABS_AGENT_ID, DEEPGRAM_API_KEY (optional; pick them up only if present)

Validate TWILIO_ACCOUNT_SID matches ^AC[0-9a-fA-F]{32}$ and TWILIO_PHONE_NUMBER matches ^\+[1-9]\d{1,14}$. If a required key is missing or invalid, show which one and ask the user to fix the .env and re-run, or fall back to manual entry.

If found and valid, choose engine from what's present (default openai_realtime if OPENAI_API_KEY is set), then jump to Step 5.

Otherwise (manual entry), continue with Step 2.

Step 2 — Collect Twilio credentials

Use AskUserQuestion sequentially. Validate each answer before moving on. If invalid, re-prompt.

  1. Twilio Account SID — must match ^AC[0-9a-fA-F]{32}$
  2. Twilio Auth Token — non-empty, opaque
  3. Twilio Phone Number — E.164, must match ^\+[1-9]\d{1,14}$

Read the full file on GitHub · 115 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.

  1. 4d ago First seen · 115 lines · 11 tokens per session scan B ef1d838a32c5

Subscribe to this mod's changes

setup is a command published in the GitHub repository PatterAI/awesome-claude-call (8 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 1,275 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.