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/punt-labs/vox/callgit clone --depth 1 https://github.com/punt-labs/voxWrote 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/punt-labs/vox/call)<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>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 | $0.00010 | $0.00615 |
| Opus 5 | $0.00005 | $0.00308 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
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.
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 lettingvox call startdiscover one. Required when more than one Claude Code session is active for this directory --vox call startrefuses to guess (verified unsafe indocs/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.
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.
- 3d ago First seen · 49 lines · 10 tokens per session scan A 5c5d4dcf36c1
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.
Other commands, from other repositories
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
feedback-to-us
Tell us how the prfaq plugin is working for you (anonymous 1-5 feedback).
badge
Generate a stage-colored badge and embed it in your README.