call

call is a command for coding agents from punt-labs/vox. It costs 10 tokens per session (615 once invoked), scanned A, original, MIT.

A command for starting, moving, or stopping a live voice conversation with the current coding-agent session.

In plain words
What is it for?
Use it to begin a microphone-based call, attach it to a chosen session, transfer it to another session, or hang up.
Why use it?
It lets you control a voice call from the command line, including scripted calls for demos or automated tests.

Command

Part of the vox-dev plugin — 10 commands, 9 hooks 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/punt-labs/vox/call
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

Or install vox-dev, the plugin that ships this one along with the rest of its 10 commands, 9 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 call

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/vox/call.svg)](https://agentmods.dev/commands/punt-labs/vox/call)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/vox/call"><img src="https://agentmods.dev/badge/commands/punt-labs/vox/call.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00010 $0.00615
Opus 5 $0.00005 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00061

Measured 3d ago against content hash 5c5d4dcf36c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

call 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 3d 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.

plugin/commands/call.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/call command

Conversation Mode: a live voice call between the human and this Claude Code session, mediated by voxd. Unlike /music and /rec, there is no mic:call MCP tool yet -- every /call verb shells out to the vox call CLI instead.

Usage

  • /call start -- start a real call: real microphone capture, transcribed by ElevenLabs. This is the primary way to place a call.
  • /call start --script <path> -- dev/test path: read scripted turns from a JSON Lines file ({"text": ..., "confidence": ...} per line) instead of the microphone -- no hardware, no ElevenLabs credentials, no network. For demos and CI.
  • /call start [--script <path>] --session <id> -- attach to a specific session id instead of letting vox call start discover one. Required when more than one Claude Code session is active for this directory -- vox call start refuses to guess (verified unsafe in docs/conversation-mode-session-attach-adr.md).
  • /call transfer [--session <id>] -- ask the running call to re-attach to a different active session, without ending the call.
  • /call stop -- ask the running call to hang up (FR-2's explicit end).

Implementation

Parse $ARGUMENTS and run the matching vox call <verb> command via Bash, passing --script/--session through verbatim. vox call start blocks in the foreground for the life of the call; stop and transfer are fire-and-forget signals to whichever vox call start process is running, via the cross-process control file (src/punt_vox/voxd/conversation_mode/call_control.py).

While a call is active, plugin/hooks/call-lock.sh blocks the human's own interactive UserPromptSubmit, self-clearing if the holding process has died. The escape hatch is never blocked by its own lock: /call stop and /call transfer prompts pass the hook unconditionally, and the call's own turns -- relayed through a claude -p --resume subprocess (src/punt_vox/voxd/conversation_mode/claude_session_attach.py) -- carry VOX_CALL_RELAY=1 in that subprocess's own environment, set by the process that spawns it, so the lock the call holds for the human's input never blocks its own traffic.

Read the full file on GitHub · 49 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. 3d ago First seen · 49 lines · 10 tokens per session scan A 5c5d4dcf36c1

Subscribe to this mod's changes

call is a command published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 615 once invoked, about $0.0001 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.