A voice-session tool for holding an ongoing conversation with a coding agent through a microphone. It supports starting, continuing, and ending live voice sessions.

Use it to start voice mode, listen for requests, handle spoken tasks, and close the session.

It removes the need to type during voice-based reviews or other continuous conversations.

livechat — Skill for Claude Code and Codex by brunocramos

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.

Any agent

npx skills add brunocramos/livechat-mcp --skill livechat

Clone the repo

git clone --depth 1 https://github.com/brunocramos/livechat-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brunocramos/livechat-mcp/livechat/github.svg)](https://agentmods.dev/skills/brunocramos/livechat-mcp/livechat)

Your own site

<a href="https://agentmods.dev/skills/brunocramos/livechat-mcp/livechat"><img src="https://agentmods.dev/badge/skills/brunocramos/livechat-mcp/livechat/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/brunocramos/livechat-mcp/livechat"><img src="https://agentmods.dev/badge/skills/brunocramos/livechat-mcp/livechat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 454 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00454
Opus 5	$0.00028	$0.00227
Sonnet 5	$0.00011	$0.00091
Haiku 4.5	$0.00006	$0.00045

Measured 8d ago against content hash 02d8ff848348, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

livechat 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 8d 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.

skills/livechat/SKILL.md · 42 lines

What it actually says

Livechat

Use the livechat MCP tools to run a continuous voice session.

Start

Before calling any MCP tool, print exactly:

Listening — go ahead.
Call reset_voice_session once, right after the announcement and before the first get_voice_input. The MCP server is long-lived; this clears any stale shutdown flag from a prior /endlivechat in the same process so the new session starts cleanly. On a fresh server it's a safe no-op. Do NOT call reset_voice_session again during the loop.
Call get_voice_input.
For real speech, echo the transcription before acting:

> "<exact text returned by get_voice_input>"
Treat the transcription as the user's next request. Act on it normally.
After completing each request, immediately call get_voice_input again to continue the loop.

Tool Results

__NO_INPUT__: do not echo it. Call get_voice_input again.
__END_SESSION__: do not echo it. Stop the loop and summarize the session briefly.
__ALREADY_RUNNING__:<pid>: do not echo it. Tell the user another voice session is active and ask whether to take over from this window. If they agree, call take_over_voice_session; on OK, print Listening — go ahead. again and resume with get_voice_input.

End

When the user asks to end livechat or stop voice mode, call end_voice_session. After calling this tool, do not call get_voice_input again. Instead, stop the loop and summarize what was accomplished.

Keep responses concise during voice mode. The user is actively speaking and expects the loop to continue until the session ends.

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.

8d ago First seen · 42 lines · 56 tokens per session scan A 02d8ff848348

Subscribe to this mod's changes

livechat is a skill published in the GitHub repository brunocramos/livechat-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 454 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens