NemoNotch: Instructions file for Claude Code

AGENTS.md

NemoNotch AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from GaoZimeng0425/NemoNotch. It costs 31,344 tokens per session, scanned C, a copy of superpowers AGENTS.md, MIT.

Project instructions for NemoNotch, an interactive MacBook panel that uses the notch area as an information hub. The listed instructions refer to a CLAUDE.md file.

In plain words
What is it for?
Following the project's instructions during AI-assisted development of NemoNotch.
Why use it?
They provide project-specific guidance to an AI coding agent working on NemoNotch.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is GaoZimeng0425/NemoNotch's own configuration. It tells Claude Code, Codex and OpenCode how to work on NemoNotch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NemoNotch configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/gaozimeng/Learn/macOS/.

Reuse

Borrowing it

Nothing to install: this file belongs to GaoZimeng0425/NemoNotch. 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/GaoZimeng0425/NemoNotch/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/GaoZimeng0425/NemoNotch

Made for: Claude Code, 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.

agentmods badge for NemoNotch AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gaozimeng0425/nemonotch/agents-md/github.svg)](https://agentmods.dev/instructions/gaozimeng0425/nemonotch/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gaozimeng0425/nemonotch/agents-md"><img src="https://agentmods.dev/badge/instructions/gaozimeng0425/nemonotch/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.

agentmods 80×15 button for NemoNotch AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gaozimeng0425/nemonotch/agents-md"><img src="https://agentmods.dev/badge/instructions/gaozimeng0425/nemonotch/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31,344 This file is loaded in full into every session.
When invoked 31,344 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.31344 $0.31344
Opus 5.5 $0.12538 $0.12538
Sonnet 5.5 $0.06269 $0.06269
Haiku 4.5 $0.03134 $0.03134

Measured 8d ago against content hash 28ce56c66505, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

NemoNotch AGENTS.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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

**Ownership marker + reconciliation.** `~/.NemoNotch/keep-awake.enabled` records "we turned this on". Written *before* the `pmset` call, so a crash in between still leaves a trace the next launch can recognize. `KeepAwak

Reads agent configuration directoriesmediumAgent snooping

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

S["~/.claude/settings.json"]
Origin

This is a copy

100% identical to superpowers AGENTS.md — 686 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 672 lines

How it starts

The opening of the file, as written. The whole thing — 672 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NemoNotch — AGENTS.md

Project Overview

NemoNotch is a macOS notch utility that provides an interactive floating panel in the MacBook notch area, integrating media controls, calendar events, AI CLI monitoring (Claude Code / Gemini CLI / opencode / zcode), multi-agent monitoring (OpenClaw / Hermes-agent), and an app launcher.

Tech Stack

  • Swift 6 + SwiftUI, macOS only, depends on CocoaLumberjack, KeyboardShortcuts, mediaremote-adapter (perl-bridge media control)
  • Key frameworks: AppKit (NSWindow), MediaPlayer, EventKit, IOKit

Project Structure

NemoNotch/
├── NemoNotchApp.swift           # Entry point, MenuBarExtra, global hotkeys, service assembly
├── Models/                      # Data models (Tab, AppSettings, AIProvider, PlaybackState, MultiAgentMonitor, etc.)
├── Notch/                       # Notch UI core (window, animation, event monitoring, TabBar, HUD)
├── Tabs/                        # Tab content views (AIChatTab renders AI sessions AND OpenClaw/Hermes agents in one merged list)
├── Services/                    # Background services (media, calendar, AI CLI, launcher, HermesService, etc.)
├── Settings/                    # Settings UI
├── PermissionFlow/              # Drag-to-authorize guide for System Settings privacy panes
└── Helpers/                     # Utilities (MarkdownRenderer, ClaudeCrabIcon, ToolStyles)

Architecture

Overview

graph TB
    subgraph Entry["App Entry"]
        App["NemoNotchApp<br/>@main"]
        AD["AppDelegate<br/>Lifecycle only"]
        DEPD["AppDependencies<br/>Composition root (build, notchContent)"]
    end

    subgraph Services["Service Layer — all @Observable"]
        MS["MediaService<br/>MediaRemote (notifications) + NowPlayingCLI (read) + MediaRemoteCommander (control)"]
        AIM["AICLIMonitorService<br/>Unified AI entry + owns AISessionStore"]
        AISS["AISessionStore<br/>Central AI session truth source (@Observable)"]
        CCS["ClaudeCodeService<br/>AIProvider impl<br/>HookServer + ConversationParser"]
        GP["GeminiProvider<br/>AIProvider impl<br/>GeminiConversationParser"]
        REG["AgentMonitorRegistry<br/>Unifies agent monitors"]
        OCS["OpenClawService<br/>WebSocket client (MultiAgentMonitor)"]
        HES["HermesService<br/>HTTP API client (MultiAgentMonitor)"]
        CS["CalendarService<br/>EventKit"]
        LS["LauncherService<br/>App search & launch"]
        NS["NotificationService<br/>Dock Accessibility API"]
        WS["WeatherService<br/>Open-Meteo primary + wttr.in fallback"]
        UQS["UsageQuotaService<br/>Claude + Codex + Gemini usage quota"]
        HUD["HUDService<br/>Volume/Brightness/Battery + charging notch capsule"]
        KAS["KeepAwakeService<br/>pmset -a disablesleep via osascript admin auth<br/>owns LidMonitor (clamshell → display off)"]
        SYS["SystemService<br/>CPU/memory/disk sampling (SystemTab)"]
        TS["TaskStore<br/>Persistent TODO list (~/.NemoNotch/tasks.json)"]
        PHS["PomodoroHistoryStore<br/>Append-only history (~/.NemoNotch/pomodoro-history.json)"]
        PTS["PomodoroTimerService<br/>State machine + tick + end-alert pipeline"]
        NPM["NotificationPermissionMonitor<br/>UNUserNotificationCenter probe"]
        HK["Hotkeys.swift<br/>KeyboardShortcuts registration (AppDelegate.setupHotkeys)"]
        CFS["CompletionFlashService<br/>Observes AISessionStore + AgentMonitorRegistry<br/>throttle/merge → drives flash + toast"]
        BTS["BluetoothService<br/>IOBluetooth audio connect/disconnect → notch capsule"]
        CDM["CalendarDueMonitor<br/>10s tick → due calendar events → unified flash"]
        CGL["CrashGuard<br/>fatal-signal self-restart (loop-guarded)"]
    end

    subgraph NotchUI["Notch UI Layer"]
        NC["NotchCoordinator<br/>Open/close state & animation"]
        NW["NotchWindow<br/>NSPanel .statusBar+8"]
        NV["NotchView<br/>SwiftUI main view"]
        EM["EventMonitor<br/>Mouse event listener"]
        CB["CompactBadge<br/>Collapsed icons"]
        TB["TabBarView<br/>Tab navigation"]
        HO["HUDOverlayView<br/>Volume/Brightness overlay"]
    end

    subgraph Tabs["Tabs"]
        OT["OverviewTab<br/>Media + Calendar + Weather"]
        AT["AIChatTab<br/>AI sessions + OpenClaw/Hermes agents, one merged list"]
        LT["LauncherTab"]
        PT["PomodoroTab<br/>Idle stats + TODO list + active pie"]
        ST["SystemTab"]
    end

    subgraph Settings["Settings"]
        AS["AppSettings<br/>UserDefaults persistence"]
        SW["SettingsWindow"]
        SV["SettingsView"]
    end

    App --> AD
    AD -->|"creates & owns"| Services
    AD -->|"creates"| NC
    AIM --> CCS
    AIM --> GP
    AIM -->|"owns"| AISS
    CCS -.->|"mutate"| AISS
    GP -.->|"mutate"| AISS
    REG -->|"registers"| OCS
    REG -->|"registers"| HES
    NC --> NW --> NV
    NV --> Tabs
    NV --> CB
    NV --> TB
    NV --> HO
    EM -->|"mouse events"| NC
    HK -->|"hotkeys"| NC
    AS --> SV

    Services -.->|"@Environment injection"| NV
    AS -.->|"@Environment injection"| NV

Read the full file on GitHub · 672 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. 8d ago Changed · +78 lines · +6,502 tokens per session 28ce56c66505
  2. 16d ago Changed · +22 lines · +3,447 tokens per session fec08789afaa
  3. 28d ago Changed · +571 lines · +21,391 tokens per session scan A → C 61532031bd6b
  4. 1mo ago First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810

Subscribe to this mod's changes

NemoNotch AGENTS.md is an instructions file published in the GitHub repository GaoZimeng0425/NemoNotch (9 stars, last pushed yesterday), licensed MIT. It adds 31,344 tokens to every session, about $0.1254 per session on Opus 5.5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). It is 100% identical to superpowers AGENTS.md, differing in 686 lines, and is treated as a copy.

Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens