agentmods.dev

Bark CLAUDE.md

A project instruction file for Bark, an iOS app that sends custom push notifications over Apple’s notification service. It records the project structure, dependencies, development commands, testing, and build procedures.

In plain words
What is it for?
Use it as a reference when installing dependencies, running tests with Fastlane or xcodebuild, building the app, or preparing a TestFlight build.
Why use it?
It gives a coding agent the project context needed to work consistently. It also records that CocoaPods dependencies should be installed and that the workspace should be used instead of the project file.

Instructions file

9.0k 15d ago A scan 1,502 tokens original MIT
View the source file Finb/Bark
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/finb/bark/claude-md
Clone the repo
git clone --depth 1 https://github.com/Finb/Bark
Per session 1,502 This file is loaded in full into every session.
When invoked 1,502 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01502 $0.01502
Opus 5 $0.00751 $0.00751
Sonnet 5 $0.00300 $0.00300
Haiku 4.5 $0.00150 $0.00150

Measured 3d ago against content hash 9a9e16e47ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Bark CLAUDE.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 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.

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.

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 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

Bark is an iOS push notification tool app that allows users to send custom push notifications to their devices via HTTP requests. It leverages Apple Push Notification service (APNs) and supports advanced iOS notification features like grouping, custom icons/sounds, time-sensitive notifications, critical alerts, and end-to-end encryption.

Development Commands

Dependencies

# Install CocoaPods dependencies
pod install

# Always work with the workspace, not the project
# Open: Bark.xcworkspace

Testing

# Run tests via fastlane
bundle exec fastlane tests

# Run tests via xcodebuild
xcodebuild test -workspace Bark.xcworkspace -scheme Bark

Building

# Build the app
xcodebuild -workspace Bark.xcworkspace -scheme Bark build

# Build for TestFlight (requires proper certificates and environment variables)
bundle exec fastlane beta

Architecture

Core Components

Main App Target (Bark/)

  • Entry point: AppDelegate.swift - handles app lifecycle, APNs registration, Realm setup
  • AppDelegate+Realm.swift - Realm database initialization and migration logic
  • Realm schema version: 17 (see RealmConfiguration.swift)

Notification Extensions

  1. NotificationServiceExtension/ - UNNotificationServiceExtension that processes incoming notifications
    • NotificationService.swift - orchestrates notification processing through a pipeline of processors
    • Processor/ directory contains specialized processors that run sequentially:
      • CiphertextProcessor - decrypts encrypted push content (must run first)
      • MarkdownProcessor - renders markdown in notification body
      • LevelProcessor - handles notification levels (active/timeSensitive/passive/critical)
      • BadgeProcessor - manages app badge count
      • AutoCopyProcessor - auto-copies content to clipboard
      • ArchiveProcessor - saves message to Realm database
      • MuteProcessor - handles group muting
      • CallProcessor - plays repeating sound for 30 seconds
      • ImageProcessor - downloads and attaches images
      • IconProcessor - sets custom notification icon (iOS 15+, runs last as it may timeout)

Read the full file on GitHub · 149 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 · 149 lines · 1,502 tokens per session scan A 9a9e16e47ef9

Subscribe to this mod's changes

Bark CLAUDE.md is an instructions file published in the GitHub repository Finb/Bark (8,970 stars, last pushed 15d ago), licensed MIT. It adds 1,502 tokens to every session, about $0.0075 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.

iosios-appios-swiftmvvmmvvm-architecturerxswift
Related

Other instructions, from other repositories

livtet-mobile AGENTS.md

Instructions for olamaelcu/livtet-mobile, covering agent guidelines for mobile/, where the rules live, cross-cutting rules, both apps are separate products and work in a worktree.

olamaelcu/livtet-mobile · 914 tokens

speech-swift AGENTS.md

Instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.

soniqo/speech-swift · 5,001 tokens

maui-labs AGENTS.md

Instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.

dotnet/maui-labs · 5,419 tokens

AppClaw CLAUDE.md

Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).

appclawhq/AppClaw · 2,529 tokens

ios-simulator-skill CLAUDE.md

Instructions for conorluddy/ios-simulator-skill, covering claude.md - developer guide, project overview, project structure, architecture patterns and pattern 1: class-based script design.

conorluddy/ios-simulator-skill · 2,315 tokens

ampere AGENTS.md

Instructions for socket-link/ampere, covering agents.md, concepts, development commands, build & test and code quality.

socket-link/ampere · 1,694 tokens