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.
npx agentmods add commands/patterai/awesome-claude-call/setupgit clone --depth 1 https://github.com/PatterAI/awesome-claude-callWrote 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/commands/patterai/awesome-claude-call/setup)<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>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 | $0.00011 | $0.01275 |
| Opus 5 | $0.00005 | $0.00638 |
| Sonnet 5 | $0.00002 | $0.00255 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 0600 "$HOME/.claude-call/credentials" 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 "$HOME/.claude-call/credentials" && echo EXISTS || echo MISSING
If EXISTS, ask the user with AskUserQuestion: "Existing credentials found at ~/.claude-call/credentials. Overwrite?" (Yes / No). If No, exit with the message "Setup cancelled. Existing credentials kept."
Step 1.5 — Choose credential source
Use AskUserQuestion: "How do you want to provide credentials?"
- Enter manually — Walk through Twilio + voice-engine prompts.
- Import from a
.envfile — Skip the prompts; read keys from a path you give me.
If the user picks Import from .env, ask AskUserQuestion for the absolute path. Read it with the Read tool. Extract these keys (case-sensitive, last value wins):
TWILIO_ACCOUNT_SID,TWILIO_AUTH_TOKEN,TWILIO_PHONE_NUMBER(required)OPENAI_API_KEY(required for the default engine)ELEVENLABS_API_KEY,ELEVENLABS_AGENT_ID,DEEPGRAM_API_KEY(optional; pick them up only if present)
Validate TWILIO_ACCOUNT_SID matches ^AC[0-9a-fA-F]{32}$ and TWILIO_PHONE_NUMBER matches ^\+[1-9]\d{1,14}$. If a required key is missing or invalid, show which one and ask the user to fix the .env and re-run, or fall back to manual entry.
If found and valid, choose engine from what's present (default openai_realtime if OPENAI_API_KEY is set), then jump to Step 5.
Otherwise (manual entry), continue with Step 2.
Step 2 — Collect Twilio credentials
Use AskUserQuestion sequentially. Validate each answer before moving on. If invalid, re-prompt.
- Twilio Account SID — must match
^AC[0-9a-fA-F]{32}$ - Twilio Auth Token — non-empty, opaque
- Twilio Phone Number — E.164, must match
^\+[1-9]\d{1,14}$
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.
- 4d ago First seen · 115 lines · 11 tokens per session scan B ef1d838a32c5
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.
Other commands, from other repositories
tts-status
Show current TTS plugin status.
tts-setup
Set up TTS with a provider (elevenlabs, openai, google, amazon, azure, edge, kitten, tada, fish, gemini, local).
tts-off
Disable text-to-speech for Claude responses.
tts-on
Enable text-to-speech for Claude responses.
tts-stop
Stop TTS playback immediately.
init
Install the formatters this repository needs, with every command visible before it runs.