What is limboo CLAUDE.md?

A project instruction file for Limboo, a local-first desktop app that provides the workspace around an AI coding agent.

Use it when developing Limboo, navigating its three Electron contexts, or checking how sessions and project services are organized.

It explains the project’s architecture and rules so an agent can work safely across sessions, repositories, terminals, memory, permissions, and interface code.

How limboo-ai/limboo configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to limboo-ai/limboo. 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/limboo-ai/limboo/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/limboo-ai/limboo

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/limboo-ai/limboo/claude-md/github.svg)](https://agentmods.dev/instructions/limboo-ai/limboo/claude-md)

Your own site

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

Per session 25,202 This file is loaded in full into every session.

When invoked 25,202 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.25202	$0.25202
Opus 5	$0.12601	$0.12601
Sonnet 5	$0.05040	$0.05040
Haiku 4.5	$0.02520	$0.02520

Measured 5d ago against content hash 3ca2aab3e4f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

limboo CLAUDE.md scanned grade A with 1 finding 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Renderer = UI only.** No `fs`, no `child_process`, no git, no terminal logic,

CLAUDE.md · 1,520 lines

How it starts

The opening of the file, as written. The whole thing — 1,520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Operational guide and deep context for any AI coding agent (Claude, etc.) working in this repository. Read this first. It explains what Limboo is, how the code is organized, the rules you must follow, and what is and is not built yet.

Companion document: project.md holds the full product/architecture vision. CLAUDE.md (this file) is the practical, code-level contract for working in the repo. When the two disagree about current reality, trust CLAUDE.md.

1. What is Limboo?

Limboo is a local-first desktop application that acts as the operating system for AI software development. It is not an AI model. Instead, it provides the environment around a connected coding agent: project management, sessions, file watching, repository indexing, git operations, terminal execution, memory, permissions, context, search, and UI.

Core idea: every development task happens inside a Session. A session bundles a repository, branch, chat history, agent, terminal history, checkpoints, permissions, context, memory, tasks, and generated files into one workspace.

Guiding principles (from project.md §4): Fast, Local, Private, Modular, Secure, Responsive, Observable, Predictable, Recoverable. There is no backend. Limboo itself makes exactly three kinds of outbound request, and no others may be added without amending this paragraph:

The connected coding agent talking to its AI provider.
Contributor avatars — so commit history can show a real face. Two steps, both gated by the single settings.git.avatars.enabled switch:
- Identity. A GitHub noreply commit address already encodes the account (<id>+<login>@users.noreply.github.com), so it needs no lookup. Every other address — which is most real history — can only be resolved by GitHub, so GhManager.commitAuthors calls one read-only endpoint, GET /repos/{owner}/{repo}/commits, through the gh CLI. It returns commit.author.email alongside the resolved author.{login,avatar_url}, mapping a whole page of history per request. This tells GitHub which repository is being browsed — the reason the setting exists and says so.
- Image. main/managers/gh/avatars.ts fetches the picture from GitHub's avatar host: host-allowlisted, https-only, manual redirect screening, byte- and time-capped, magic-byte sniffed (no SVG), and screened by isEmbeddedAvatar before it can reach an <img src>.

Read the full file on GitHub · 1,520 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.

5d ago Changed · +27 lines · +454 tokens per session 3ca2aab3e4f6
10d ago First seen · 1,493 lines · 24,748 tokens per session scan A 5a8be0d66e71

Subscribe to this mod's changes

limboo CLAUDE.md is an instructions file published in the GitHub repository limboo-ai/limboo (92 stars, last pushed yesterday), licensed MIT. It adds 25,202 tokens to every session, about $0.1260 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CI and CD Claude Code Data and AI agent desktop-app electron forge-app

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

limboo: Instructions file for Claude Code