agentmods.dev

agent-island: Instructions file for Claude Code

CLAUDE.md

agent-island CLAUDE.md is an instructions file for Claude Code from javen-yan/agent-island. It costs 1,047 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for Agent Island, a macOS SwiftUI application with a Rust bridge, which is a component that connects the app to Rust code. It documents build, dependency, test, and analysis commands.

In plain words
What is it for?
Use it to build signed or unsigned versions, resolve Swift dependencies, compile the Rust bridge, run Rust tests, and perform Swift analysis.
Why use it?
It tells a coding agent how to build the app and bridge consistently and how to run the relevant checks. This avoids guessing between Xcode, shell scripts, and Cargo commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is javen-yan/agent-island's own configuration. It tells Claude Code how to work on agent-island 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 agent-island configures →

not rated 24repo 5mo ago A scan 1,047 tokens original Apache-2.0
View source ↗ javen-yan/agent-island
Reuse

Borrowing it

Nothing to install: this file belongs to javen-yan/agent-island. 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/javen-yan/agent-island/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/javen-yan/agent-island

Made for: Claude Code.

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 agent-island CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/javen-yan/agent-island/claude-md/github.svg)](https://agentmods.dev/instructions/javen-yan/agent-island/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/javen-yan/agent-island/claude-md"><img src="https://agentmods.dev/badge/instructions/javen-yan/agent-island/claude-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 agent-island CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/javen-yan/agent-island/claude-md"><img src="https://agentmods.dev/badge/instructions/javen-yan/agent-island/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,047 This file is loaded in full into every session.
When invoked 1,047 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01047 $0.01047
Opus 5 $0.00524 $0.00524
Sonnet 5 $0.00209 $0.00209
Haiku 4.5 $0.00105 $0.00105

Measured 9d ago against content hash 50ca70a522b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-island 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 9d 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 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, test, and development commands

Main app (macOS SwiftUI)

  • Build app + bridge (default local flow):
    • ./scripts/build.sh
  • Build app in unsigned mode (CI-style / local without signing):
    • AGENT_ISLAND_NO_SIGN=1 ./scripts/build.sh
  • Build in Xcode via CLI (Debug):
    • xcodebuild build -project AgentIsland.xcodeproj -scheme AgentIsland -configuration Debug
  • Resolve Swift package dependencies:
    • xcodebuild -resolvePackageDependencies -project AgentIsland.xcodeproj -scheme AgentIsland

Rust bridge (bridge-rs)

  • Build release bridge binary:
    • ./scripts/build-rust-bridge.sh
    • or cargo build --release --manifest-path bridge-rs/Cargo.toml
  • Run bridge tests:
    • cargo test --manifest-path bridge-rs/Cargo.toml
  • Run a single Rust test:
    • cargo test --manifest-path bridge-rs/Cargo.toml <test_name>

Lint / analysis

This repo does not define a dedicated lint script. Use platform-native checks:

  • Swift static analysis:
    • xcodebuild analyze -project AgentIsland.xcodeproj -scheme AgentIsland -configuration Debug
  • Rust linting / formatting checks:
    • cargo clippy --manifest-path bridge-rs/Cargo.toml --all-targets -- -D warnings
    • cargo fmt --manifest-path bridge-rs/Cargo.toml --check

Packaging / release helpers

  • Local release packaging workflow (notarization/DMG/appcast/release automation helper):
    • ./scripts/create-release.sh

High-level architecture

AgentIsland is a macOS menu bar runtime that normalizes hook events from multiple CLI agents (Claude, Codex, Gemini) into one internal protocol and one shared UI/state engine.

Core runtime layers

  1. Official hook protocols (agent-specific)

    • Each agent emits its own hook/event format.

  2. Rust bridge normalization (bridge-rs)

    • Entrypoint: bridge-rs/src/main.rs
    • Dispatch: bridge-rs/src/dispatcher.rs
    • Shared payload model: bridge-rs/src/protocol.rs
    • Agent adapters: bridge-rs/src/adapter/{claude,codex,gemini}.rs
    • Output is a normalized HookPayload with stable fields used by Swift.

Read the full file on GitHub · 109 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. 9d ago First seen · 109 lines · 1,047 tokens per session scan A 50ca70a522b1

Subscribe to this mod's changes

agent-island CLAUDE.md is an instructions file published in the GitHub repository javen-yan/agent-island (24 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,047 tokens to every session, about $0.0052 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 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 · 3,735 tokens