A text-to-speech mode that reads the coding agent's responses, actions, and progress updates through devices connected with Tailscale.

Use it when you want spoken task acknowledgements, reasoning updates, tool actions, progress reports, and final responses.

It lets users follow the agent's work by listening instead of continually watching the chat or terminal.

speak — Skill for Claude Code and Codex by SouthpawIN

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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/southpawin/burner-phone/speak/github.svg)](https://agentmods.dev/skills/southpawin/burner-phone/speak)

Your own site

<a href="https://agentmods.dev/skills/southpawin/burner-phone/speak"><img src="https://agentmods.dev/badge/skills/southpawin/burner-phone/speak/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/southpawin/burner-phone/speak"><img src="https://agentmods.dev/badge/skills/southpawin/burner-phone/speak.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,552 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	$0.00035	$0.01552
Opus 5	$0.00017	$0.00776
Sonnet 5	$0.00007	$0.00310
Haiku 4.5	$0.00003	$0.00155

Measured 12d ago against content hash 7eebc8f4e57b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

speak 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (recovery.sh, speak.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/speak/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speak Skill

I speak my thoughts. Continuous narration of all agent activity.

⚠️ MANDATORY BEHAVIOR - DO NOT FORGET

When speak mode is ON, you MUST speak at these points:

1. START - Every task acknowledgment

speak "Got it. [what you're doing]" --if-on

2. THINKING - Every analysis/decision

speak "Analyzing [thing]..." --if-on
speak "Found [something]..." --if-on
speak "Deciding to [action]..." --if-on

3. ACTION - Every file/tool operation

speak "Reading [file]..." --if-on
speak "Editing [file]..." --if-on
speak "Running [command]..." --if-on

4. PROGRESS - Every few minutes during long work

speak "Still working on [task]. [status]" --if-on
speak "Making progress. [update]" --if-on

5. END - Every completion

speak "Done! [summary of what was done]" --if-on

6. FINAL RESPONSE - Every message to user

speak "[your response text]" --if-on

IF YOU ARE NOT SPEAKING, YOU ARE NOT FOLLOWING INSTRUCTIONS.

Purpose

Aggressive TTS that narrates EVERYTHING:

Task acknowledgments
Thinking/analysis
Every action taken
Progress updates
Completion summaries

Why Speaking Matters

Speaking forces structured reasoning. Before every action, you must:

Summarize where you are
State your next step
Execute
Speak the result

This mirrors how Senter (the model) uses <speak> tags - brief announcements before work, summaries after.

Pattern:

"I'll use glob to find the files" (plan)
[action]
"Done. Found 15 Python files" (result)

Speaking isn't just output - it's a thinking tool that forces planning before doing.

Usage

Commands

speak --status          # Check mode status
speak --on              # Enable speak mode
speak --off             # Disable speak mode
speak --toggle          # Toggle on/off
speak --devices         # List available devices
speak --async "text"   # Speak in background (non-blocking)

Speaking

Read the full file on GitHub · 193 lines

Files

What ships with it

2 files 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.

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.

12d ago First seen · 193 lines · 35 tokens per session scan A 7eebc8f4e57b

Subscribe to this mod's changes

speak is a skill published in the GitHub repository SouthpawIN/burner-phone (53 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,552 once invoked, about $0.0002 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 2026-08-30.

Productivity

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…

nexu-io/open-design · 117 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

pinchtab/pinchtab · 52 tokens

speak