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 DavidROliverBA/ArchitectKB --skill voice-chatgit clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBWrote 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/davidroliverba/architectkb/voice-chat)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/voice-chat"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/voice-chat/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/davidroliverba/architectkb/voice-chat"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/voice-chat.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 | $0.00013 | $0.01128 |
| Opus 5 | $0.00006 | $0.00564 |
| Sonnet 5 | $0.00003 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
voice-chat 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 9d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/voice-chat
Voice-controlled Claude Code. Speak your commands/questions, Claude processes them verbatim (as if you typed them), and responds with Inworld Olivia voice.
Usage
/voice-chat # Start voice-controlled mode
/voice-chat stop # Exit voice mode
Requirements (from .claude/voice-chat-requirements.md)
R1: Voice Input → Claude Code Verbatim
Your spoken words are transcribed and passed directly to Claude Code — exactly as if you typed them.
R2: Response in Inworld Olivia Voice
Claude Code's response is spoken using Inworld TTS with Olivia voice.
Prerequisites
-
voice-bridge server running with
INWORLD_API_KEYset:cd ~/Documents/GitHub/voice-bridge VOICE_BACKEND=inworld INWORLD_API_KEY=<your-key> npm start -
Microphone permissions granted
Instructions
Starting Voice Mode
When /voice-chat is invoked:
-
Announce start:
mcp__voice-mcp__voice_speak({ text: "Voice mode active. Speak your command.", voice_id: "Olivia", speed: 1.0 }) -
Display:
🎤 **Listening...** -
Listen for voice:
mcp__voice-mcp__voice_listen({ timeout_seconds: 30, language: "en-GB" }) -
Display the transcription:
👤 **You said:** "<transcribed text>" -
CRITICAL: Process the transcribed text as if the user typed it directly.
- Do NOT interpret it as a "voice chat question"
- Execute it as a normal Claude Code command/request
- Use all available tools (Read, Edit, Grep, Bash, etc.) as needed
- Generate your normal response
-
Display speaking indicator:
🔊 **Speaking...** -
Speak the response (or summary if long):
mcp__voice-mcp__voice_speak({ text: "<response or summary>", voice_id: "Olivia", speed: 1.0, wait: true }) -
Smart Output Router - Decide what to speak:
Content Type Action Voice Says Short (< 100 words) Speak fully Full response Medium (100-300 words) Display + announce "Here's what I found" Long (> 300 words) Display only "Please read this" Contains code Display + announce "Here's the code" Contains table Display + announce "Here's a table" Error Speak Brief error description
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.
- 9d ago First seen · 173 lines · 13 tokens per session scan A 91444971821d
voice-chat is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 1,128 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.