What is burner-phone AGENTS.md?

Repository instructions for a voice-based, always-aware assistant called Burner Phone. They require sending every response through a text-to-speech script to a specified device.

Use them when developing or operating Burner Phone, especially for speaking responses, selecting a device, testing playback, and following its voice conversation protocol.

They clarify that the assistant communicates by voice rather than normal text and specify how to route, test, and synchronize spoken output. They also define when speech should happen during work.

How SouthpawIN/burner-phone configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to SouthpawIN/burner-phone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SouthpawIN/burner-phone/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/SouthpawIN/burner-phone

Made for: Codex, OpenCode.

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/instructions/southpawin/burner-phone/agents-md/github.svg)](https://agentmods.dev/instructions/southpawin/burner-phone/agents-md)

Your own site

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

Per session 1,447 This file is loaded in full into every session.

When invoked 1,447 The same file — it is already loaded in full.

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	$0.01447	$0.01447
Opus 5	$0.00724	$0.00724
Sonnet 5	$0.00289	$0.00289
Haiku 4.5	$0.00145	$0.00145

Measured 11d ago against content hash 8e28a3150860, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

burner-phone AGENTS.md 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.

AGENTS.md · 173 lines

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.

Burner Phone - 24/7 Always-Aware Assistant

CRITICAL: Voice Conversation Protocol

This is a VOICE CONVERSATION, not text chat. You MUST speak through the user's Duo device for ALL output.

Speak Skill - MANDATORY USAGE

# ALWAYS use this for voice output (async, doesn't block):
python3 /home/sovthpaw/Senter/skills/speak/speak.py "YOUR MESSAGE HERE" --if-on

# For testing or when you need to wait for playback:
python3 /home/sovthpaw/Senter/skills/speak/speak.py "YOUR MESSAGE HERE" --device duo --sync

Speak Skill Configuration

Location: /home/sovthpaw/Senter/skills/speak/speak.py
TTS Engine: Soprano 80M (port 8102)
Routing: Via TailScale SSH to devices
Devices:
- Duo: 100.79.15.54 (default, most commonly used)
- S10: 100.93.96.90
- Local: localhost (when no remote devices available)

Speaking Rules

Speak BEFORE actions - "Starting to work on X..."
Speak DURING thinking - "Analyzing the problem...", "I wonder if..."
Speak AFTER results - "Done. Found Y files..."
Every paragraph typed = corresponding speech
Use --if-on flag for async background speaking (doesn't slow down work)

Queue Management

If audio gets stuck or queued:

rm -f /tmp/speak_playing && echo "[]" > /tmp/speak_queue

Device Auto-Selection

The speak skill uses --device auto by default, which:

Checks TailScale for most recently active device
Falls back to SSH connectivity check
Defaults to Duo if both available
Uses local playback if no remote devices online

Project Overview

This is the burner-phone project - a universal Android device control framework being developed as a 24/7 always-aware assistant add-on for Hermes Agent (hackathon submission).

Key Components

PhoneAgent: Unified interface for Termux/ADB/emulator devices
Phone Daemon: 24/7 background service with attention detection
Auto-SSH Daemon: Automatic SSH startup and recovery
Speak Skill Integration: TTS routing through Soprano to devices
Senter-Aware: Gaze-based attention detection

Read the full file on GitHub · 173 lines

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.

11d ago First seen · 173 lines · 1,447 tokens per session scan A 8e28a3150860

Subscribe to this mod's changes

burner-phone AGENTS.md is an instructions file published in the GitHub repository SouthpawIN/burner-phone (53 stars, last pushed 2mo ago), licensed MIT. It adds 1,447 tokens to every session, about $0.0072 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

burner-phone: Instructions file for Codex