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 skills add Glad-Labs/poindexter --skill voice-ongit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/skills/glad-labs/poindexter/voice-on)<a href="https://agentmods.dev/skills/glad-labs/poindexter/voice-on"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/voice-on/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.
<a href="https://agentmods.dev/skills/glad-labs/poindexter/voice-on"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/voice-on.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.00445 |
| Opus 5 | $0.00026 | $0.00222 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
voice-on 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 11d 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.
What it actually says
Voice On
Spins up the LiveKit ↔ Claude Code bridge for the current session: voice
in becomes the next user input via a per-session pipe; whatever Claude
generates can be sent back as voice via the voice-speak skill.
The always-on voice-agent-livekit container is unaffected — this
skill claims a separate participant identity (claude-bridge) on the
configured LiveKit room so both agents can coexist if needed.
Usage
scripts/run.sh [room]
Parameters
- room (string, optional): LiveKit room name. Defaults to
app_settings.voice_default_room(seeded as"claude-bridge").
What happens
- Calls the
voice_join_roomMCP tool — it spins up a per-session bridge worker and creates two pipe files under~/.poindexter/voice/<session_id>.{in,out}. - Returns the
session_idso subsequent skills (voice-speak,voice-off) know which bridge to talk to. - Prints "voice on, talk to me" plus the session id.
The session id is also stored in ~/.poindexter/voice/CURRENT_SESSION
so a Monitor watcher / hook can pick up new transcript lines from the
right .in pipe without the user retyping the id.
After enabling
To consume voice transcripts as user input, point a Monitor task at
the .in pipe:
Monitor: tail -F ~/.poindexter/voice/<session_id>.in
Each line emitted by the watcher is one utterance — feed it back to the session as the next user message.
To send the assistant's reply as voice, call:
voice-speak "<text>"
When done: voice-off.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 59 lines · 51 tokens per session scan A d4dde3cee195
voice-on is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 445 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.
Other skills, from other repositories
spec-generate
Product Spec Builder that helps PMs generate clear, structured, testable PRDs. Creates both full and lightweight specs for any product or platform with a guided step-by-step workflow. Output in English Markdown format.
Playwright (Automation + MCP + Scraper)
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…
product-team
A Chinese-language product development workflow led by one AI team lead taking several roles: product strategy, requirements writing, prototype creation, and user-experience review.
ux-walkthrough-skill
A user-experience review process that examines a product’s screens and user journeys against its product requirements document (PRD). It checks consistency, accessibility, errors, and whether users can complete tasks clearly.
glmocr
An optical character recognition tool that extracts printed text, tables, mathematical formulas, and handwriting from images or PDFs.
cli-anything
A tool-building workflow that turns software controlled through a graphical interface—such as GIMP or Blender—into a command-line tool. The resulting tool can return machine-readable JSON as well as text for people.