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.
npx agentmods add instructions/blitzdotdev/blitz-mac/claude-mdgit clone --depth 1 https://github.com/blitzdotdev/blitz-macWhat 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 | $0.00962 | $0.00962 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
blitz-mac 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 88 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.
Build & Run Commands
# Debug build
swift build
# Release build
swift build -c release
# Fetch pinned helper dependency
git submodule update --init --recursive
# Bundle as macOS .app (signs with Developer ID)
bash scripts/bundle.sh release
# Full release: bump version, bundle app, build pkg, deploy
npm run release
# Run tests
swift test
# Run a single test
swift test --filter BlitzTests.SimctlClientTests/testParseDeviceList
# Build installer pkg
bash scripts/build-pkg.sh
Architecture
Blitz is a native macOS SwiftUI app (requires macOS 14+) for iOS development. It provides simulator management, screen capture, App Store Connect integration, and an MCP server for Claude Code integration. Built with Swift Package Manager (no Xcode project). Source bundling also depends on the pinned ASC helper submodule in deps/App-Store-Connect-CLI-helper and a local Go toolchain.
Single-target structure
All Swift source lives in src/. Core types (process execution, simulator control, device interaction, project metadata) live alongside UI, services, and the MCP server in one executable target.
App State
Single AppState (@Observable) object at AppState.swift holds all app state. Child observable managers:
ProjectManager— project list and loadingSimulatorManager— simulator lifecycle (boot/shutdown viaSimctlClient)SimulatorStreamManager— screen capture viaScreenCaptureKit+ Metal renderingASCManager— App Store Connect API integrationProjectSetupManager— project scaffolding for different project types
Navigation
AppTab enum defines all tabs, grouped into Build (simulator, tests, assets), Release (ASC tabs), Insights, TestFlight, and Settings. ContentView uses NavigationSplitView with SidebarView + DetailView that switches on appState.activeTab.
MCP Server (Claude Code Integration)
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.
- 2d ago First seen · 88 lines · 962 tokens per session scan A 63cfa7203899
blitz-mac CLAUDE.md is an instructions file published in the GitHub repository blitzdotdev/blitz-mac (1,742 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 962 tokens to every session, about $0.0048 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.
Other instructions, from other repositories
appstore-ppp-pricing-agent-skill CLAUDE.md
Instructions for duceum/appstore-ppp-pricing-agent-skill, covering claude.md — project context for ai agents, what this project does, tech stack, architecture and key patterns.
asc-mcp AGENTS.md
Instructions for zelentsov-dev/asc-mcp, covering agents.md, language, project overview, build and run commands and build the project.
app-store-connect-mcp AGENTS.md
Instructions for erayendes/app-store-connect-mcp, covering agents.md, what this is, if a user asks you to install it, 1. agree on the profiles, then register them and 2. send the user to setup for the credentials.
app-store-screenshots-skill CLAUDE.md
Instructions for framara/app-store-screenshots-skill, covering claude.md, what this repo is, repository structure and editing guidelines.
App-Store-Connect-release-kit AGENTS.md
Instructions for raydeveloperF/App-Store-Connect-release-kit, covering asc release kit, structure, editing rules and validation.
asc-mcp CLAUDE.md
Instructions for zelentsov-dev/asc-mcp, covering claude.md, language, project overview, build and run commands and build the project.