What is lil-agents CLAUDE.md?

A set of instructions for working on the lil-agents macOS app, including its build process, architecture, and main components. The app shows animated characters on the Dock that provide access to AI command-line tools.

Use it when building the Xcode project or modifying the Dock characters, terminal sessions, shell environment, or supported AI tool connections.

It gives a coding agent the project-specific context needed to build and change the app correctly, including how its components communicate.

How ryanstephen/lil-agents configures Claude Code

About the project

lil-agents is a macOS app that places animated AI companions above the Dock and opens a chat terminal when clicked. It lets users work with Claude Code, OpenAI Codex, GitHub Copilot, or Google Gemini CLI from the menubar. Its catalogue instruction supports the app's agent workflow.

ryanstephen/lil-agents · 1,450 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to ryanstephen/lil-agents. 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/ryanstephen/lil-agents/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ryanstephen/lil-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ryanstephen/lil-agents/claude-md/github.svg)](https://agentmods.dev/instructions/ryanstephen/lil-agents/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ryanstephen/lil-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/ryanstephen/lil-agents/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ryanstephen/lil-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/ryanstephen/lil-agents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 482 This file is loaded in full into every session.

When invoked 482 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.

Model	Per session	Once invoked
Fable 5.1	$0.00482	$0.00482
Opus 5.5	$0.00193	$0.00193
Sonnet 5.5	$0.00096	$0.00096
Haiku 4.5	$0.00048	$0.00048

Measured 2mo ago against content hash a47cdb0fb407, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lil-agents 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 2mo 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 · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 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.

Building

Open lil-agents.xcodeproj in Xcode and build the LilAgents scheme. No command-line build system is configured.

Architecture Overview

This is a macOS AppKit application that displays animated characters walking on the Dock, providing a GUI for AI CLI tools.

Core Components

LilAgentsController — Central coordinator running a CVDisplayLink tick loop. Calculates Dock geometry from com.apple.dock defaults, positions characters above the Dock area.

WalkerCharacter — Individual character with:

AVPlayerLayer for transparent HEVC video animation
Per-character provider and size stored in UserDefaults ("{name}Provider", "{name}Size")
Manages popover terminal window and AI session lifecycle

AgentSession — Protocol for CLI interaction. Each provider has a session class:

ClaudeSession — NDJSON streaming (--output-format stream-json)
CodexSession, CopilotSession, GeminiSession, OpenCodeSession — similar patterns

ShellEnvironment — Resolves user's login shell PATH via /bin/zsh -l -i -c env to locate CLI binaries. Caches results. Removes CLAUDECODE/CLAUDE_CODE_ENTRYPOINT from spawned process environment to prevent nested session detection.

TerminalView — AppKit view rendering themed terminal with basic Markdown support and auto-scrolling.

PopoverTheme — Centralized styling (colors, fonts) for terminal UI.

Key Patterns

Dock positioning: Reads tilesize, persistent-apps, persistent-others, show-recents from com.apple.dock defaults to calculate Dock width
Window level: Characters use NSWindow.Level.statusBar + i where i is sorted by x-position
CLI discovery: ShellEnvironment.findBinary() checks shell PATH first, then fallback paths like ~/.local/bin, /opt/homebrew/bin
Per-character config: Each WalkerCharacter persists its own provider/size via UserDefaults with name-prefixed keys

Read the full file on GitHub · 38 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.

2mo ago First seen · 38 lines · 482 tokens per session scan A a47cdb0fb407

Subscribe to this mod's changes

lil-agents CLAUDE.md is an instructions file published in the GitHub repository ryanstephen/lil-agents (1,450 stars, last pushed 7mo ago), licensed MIT. It adds 482 tokens to every session, about $0.0019 per session on Opus 5.5. 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.

Building agents

lil-agents CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lil-agents CLAUDE.mdryanstephen/lil-agents	Instructions file	1.4k	7mo ago	MIT	A	482	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

lil-agents: Instructions file for Claude Code