PeonPing/peon-ping is a notification tool that alerts users with game-character voice lines and on-screen banners when an AI coding agent needs attention or finishes work. It helps people monitor terminal-based agents without constantly watching the terminal. Its catalogue add-ons configure or extend these notifications for coding agents and MCP clients.
Borrowing it
Nothing to install: this file belongs to PeonPing/peon-ping. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PeonPing/peon-ping/main/GEMINI.mdgit clone --depth 1 https://github.com/PeonPing/peon-pingWrote 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/instructions/peonping/peon-ping/gemini-md)<a href="https://agentmods.dev/instructions/peonping/peon-ping/gemini-md"><img src="https://agentmods.dev/badge/instructions/peonping/peon-ping/gemini-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.
<a href="https://agentmods.dev/instructions/peonping/peon-ping/gemini-md"><img src="https://agentmods.dev/badge/instructions/peonping/peon-ping/gemini-md.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 | $0.01030 | $0.01030 |
| Opus 5.5 | $0.00412 | $0.00412 |
| Sonnet 5.5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade C, and why
peon-ping GEMINI.md scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **macOS/Linux:** `curl -fsSL https://peonping.com/install | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **macOS/Linux:** `curl -fsSL https://peonping.com/install | bash` How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - peon-ping
Project Overview
peon-ping is a cross-platform (macOS, Linux, WSL, Windows) notification system that brings game character voice lines and visual overlay banners to AI coding agents. It helps developers maintain flow by providing audible and visual feedback when an agent completes a task, requires input, or encounters an error.
The project implements the Coding Event Sound Pack Specification (CESP), an open standard for coding event sounds.
Main Technologies
- Shell Scripting: Core logic in
peon.sh,relay.sh, and variousinstall.sh/uninstall.shscripts. - Python: Embedded within shell scripts for robust JSON parsing and complex logic.
- TypeScript: Used for the OpenCode adapter, MCP server, and the documentation site.
- Next.js: Powers the project's website and documentation in
docs/. - PowerShell: Provides native Windows and WSL support.
- Swift: Optimized audio playback on macOS (
peon-play.swift). - BATS (Bash Automated Testing System): Primary testing framework for shell scripts.
Architecture
- Core (
peon.sh): The primary entry point for hooks. It handles event mapping, sound selection, and triggers playback/notifications. - Adapters (
adapters/): Translation layers for various IDEs/Agents (Claude Code, Gemini CLI, GitHub Copilot, Cursor, Windsurf, etc.) to map their specific events to CESP categories. - MCP Server (
mcp/): A Model Context Protocol server that allows AI agents to trigger sounds directly via tool calls. - Relay (
relay.sh): An HTTP server that allows remote environments (SSH, Devcontainers, Codespaces) to route audio and notifications back to a local machine. - Trainer (
trainer/): A built-in exercise reminder system that piggybacks on coding sessions. - Packs: Sound packs are stored in
packs/(or~/.openpeon/packs/) and defined byopenpeon.jsonmanifests.
Building and Running
Installation
- macOS/Linux:
curl -fsSL https://peonping.com/install | bash - Windows:
Invoke-WebRequest -Uri "https://peonping.com/install.ps1" | Invoke-Expression - Homebrew:
brew install PeonPing/tap/peon-ping
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.
- 1mo ago First seen · 76 lines · 1,030 tokens per session scan C 19e813356812
peon-ping GEMINI.md is an instructions file published in the GitHub repository PeonPing/peon-ping (5,091 stars, last pushed 8d ago), licensed MIT. It adds 1,030 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.