prompt-chime CLAUDE.md

prompt-chime CLAUDE.md is an instructions file for coding agents from pick/prompt-chime. It costs 858 tokens per session, scanned B, original, MIT.

Project instructions for developing and testing prompt-chime, a notification toolkit for AI coding assistants.

In plain words
What is it for?
Use them to run end-to-end tests, manually test notifications, operate the management script, and understand the plugin's entry points.
Why use it?
They explain the repository structure, available commands, testing process, and shell-script architecture so an agent can work consistently.

Instructions file

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.

agentmods
npx agentmods add instructions/pick/prompt-chime/claude-md
Clone the repo
git clone --depth 1 https://github.com/pick/prompt-chime

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.

agentmods badge for prompt-chime CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pick/prompt-chime/claude-md.svg)](https://agentmods.dev/instructions/pick/prompt-chime/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pick/prompt-chime/claude-md"><img src="https://agentmods.dev/badge/instructions/pick/prompt-chime/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 858 This file is loaded in full into every session.
When invoked 858 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00858 $0.00858
Opus 5 $0.00429 $0.00429
Sonnet 5 $0.00172 $0.00172
Haiku 4.5 $0.00086 $0.00086

Measured 3d ago against content hash d67e8378bf11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

prompt-chime CLAUDE.md scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **`install.sh`** — Copies `scripts/` to `~/.claude/notifications/` and registers the Stop hook in `~/.claude/settings.json`
CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

prompt-chime is a cross-platform notification toolkit for AI coding assistants. It plays sounds and shows toast notifications when prompts complete. It's a Claude Code plugin that registers a Stop hook.

Commands

# Run E2E tests (requires python3)
bash scripts/test_e2e.sh

# Test a notification manually
bash scripts/notify.sh --event stop --title "Test" --body "Hello"

# Management CLI
bash scripts/manage.sh status
bash scripts/manage.sh test
bash scripts/manage.sh help

There is no build step. No package manager. No linter configured.

Architecture

The codebase is pure shell scripts (bash + PowerShell) with inline Python for JSON config manipulation. No external dependencies.

Entry Points

  • hooks/hooks.json — Claude Code Stop hook definition; triggers scripts/notify.sh async on every assistant stop
  • install.sh — Copies scripts/ to ~/.claude/notifications/ and registers the Stop hook in ~/.claude/settings.json
  • .claude-plugin/plugin.json — Plugin manifest for marketplace-style installation

Core Scripts (all in scripts/)

  • notify.sh — Main notification dispatcher. Parses args (--event, --project, --title, --body), reads config.json via embedded Python, resolves sound file, detects OS, delegates to platform script. Falls back to pure-bash grep if python3 is unavailable.
  • manage.sh — CLI for managing config (volume, quiet hours, toast, profiles, project overrides, sound selection). All config mutations go through the pyconf() helper which embeds Python code strings — user input must only pass through sys.argv, never interpolated into the Python code string.
  • platforms/windows.ps1 — Windows: Win32 MCI (mciSendString via P/Invoke) for audio (WAV+MP3), WinRT ToastNotificationManager for toasts (BalloonTip fallback). Toast fires first for instant feedback, then sound plays synchronously.
  • platforms/macos.sh — macOS: afplay for audio, osascript for toasts
  • platforms/linux.sh — Linux: paplay/pw-play/aplay for audio, notify-send for toasts
  • config.json — Default configuration (gets copied to install dir; the installed copy is what's read at runtime)
  • test_e2e.sh — E2E test suite (9 test groups: structure, sounds, config, OS detection, CLI, profiles, project overrides, security, live notification)
  • generate_meme_sounds.py — Synthesizes chiptune meme notification sounds (Mario 1-Up, Zelda secret, etc.) as WAV files into sounds/custom/. Run with python3 scripts/generate_meme_sounds.py. Output is gitignored.

Read the full file on GitHub · 60 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.

  1. 3d ago First seen · 60 lines · 858 tokens per session scan B d67e8378bf11

Subscribe to this mod's changes

prompt-chime CLAUDE.md is an instructions file published in the GitHub repository pick/prompt-chime (0 stars, last pushed 5mo ago), licensed MIT. It adds 858 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.