limux CLAUDE.md

limux CLAUDE.md is an instructions file for coding agents from am-will/limux. It costs 1,479 tokens per session, scanned A, original, MIT.

Project notes for Limux, a Linux terminal workspace manager built with GTK4, libadwaita, and libghostty, with a Unix-socket control API.

In plain words
What is it for?
Changing the terminal interface, workspace behavior, command-line commands, socket control features, or Rust code while following the project's build and test checks.
Why use it?
They explain the project's two separate programs and require checks before and after edits, reducing confusion between the graphical app and command-line tool.

Instructions file

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/am-will/limux/claude-md
Clone the repo
git clone --depth 1 https://github.com/am-will/limux

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 limux CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/am-will/limux/claude-md.svg)](https://agentmods.dev/instructions/am-will/limux/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/am-will/limux/claude-md"><img src="https://agentmods.dev/badge/instructions/am-will/limux/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,479 This file is loaded in full into every session.
When invoked 1,479 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 $0.01479 $0.01479
Opus 5 $0.00740 $0.00740
Sonnet 5 $0.00296 $0.00296
Haiku 4.5 $0.00148 $0.00148

Measured 4d ago against content hash 2436bf14ff63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

limux 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 4d 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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — project context for Claude Code

Short, Claude-oriented companion to AGENTS.md. For architecture and the full CLI surface, read AGENTS.md. For roadmap status, read docs/cmux-parity-plan.md.

What is this project?

Limux is a GTK4 + libadwaita + libghostty terminal workspace manager for Linux, ported from manaflow-ai's macOS cmux. It exposes a Unix-socket control API so coding agents can drive the GUI from a terminal inside a limux workspace.

Before editing

Run the quality gate before and after your changes:

./scripts/check.sh   # fmt --check, clippy -D warnings, test --workspace

Heads-up: as of this writing one test is failing (cli_arg_tests::hook_session_id_falls_back_to_transcript_stem, assertion at rust/limux-cli/src/main.rs:3893). Don't assume a clean baseline — run the gate first to see the current state.

The two-binary gotcha

  • target/debug/limux — the GTK app (limux-host-linux). Only understands GTK flags. Installed users get this as limux-host under libexec.
  • target/debug/limux-cli — the CLI (limux-cli), which implements agent-team, notify, hooks setup, send, read-screen, etc. Installed users get this as limux.

Run ./target/debug/limux-cli --help for the full subcommand list — treat it as the source of truth, not this file.

Finding code (anchors, not line numbers)

The crates churn, so search by symbol:

rg -n "fn agent_launch_command|fn build_agents_md" rust/limux-cli/src/main.rs
rg -n "\"agent-team\" =>"                          rust/limux-cli/src/main.rs
rg -n "PaneCallbacks \{"                           rust/limux-host-linux/src/window.rs
Task Crate / module
New agent in agent-team agent_launch_command in rust/limux-cli/src/main.rs
Generated AGENTS.md template build_agents_md in rust/limux-cli/src/main.rs
New CLI subcommand dispatch match in rust/limux-cli/src/main.rs
GUI bridge routing rust/limux-host-linux/src/control_bridge.rs
Full-vocabulary control (no GUI) limux-core::Dispatcher + ControlState
Pane / surface UI state rust/limux-host-linux/src/window.rs (PaneCallbacks)
Terminal IME / dead-key / compose rust/limux-host-linux/src/ime/ (state.rs state machine, routing.rs decide_routing / is_compose_initiator, contexts.rs GTK + ghostty wiring)
Agent-hook installers + templates hooks/ + limux hooks setup
Packaging (AppImage / AUR) scripts/package.sh, scripts/appimage-webkit.sh, PKGBUILD.template

Read the full file on GitHub · 117 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. 4d ago First seen · 117 lines · 1,479 tokens per session scan A 2436bf14ff63

Subscribe to this mod's changes

limux CLAUDE.md is an instructions file published in the GitHub repository am-will/limux (547 stars, last pushed yesterday), licensed MIT. It adds 1,479 tokens to every session, about $0.0074 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 4,345 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

next.js 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