limux: Instructions file for Claude Code

CLAUDE.md

limux CLAUDE.md is an instructions file for Claude Code from am-will/limux. It costs 1,587 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 for Claude Code

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

This is am-will/limux's own configuration. It tells Claude Code how to work on limux 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 limux configures →

Reuse

Borrowing it

Nothing to install: this file belongs to am-will/limux. 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/am-will/limux/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/am-will/limux

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 limux CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/am-will/limux/claude-md/github.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/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 limux CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,587 This file is loaded in full into every session.
When invoked 1,587 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 $0.01587 $0.01587
Opus 5.5 $0.00635 $0.00635
Sonnet 5.5 $0.00317 $0.00317
Haiku 4.5 $0.00159 $0.00159

Measured 1mo ago against content hash 7ee7bf26c62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 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 · 123 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. 1mo ago Changed · +6 lines · +108 tokens per session 7ee7bf26c62c
  2. 2mo 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 (561 stars, last pushed 7d ago), licensed MIT. It adds 1,587 tokens to every session, about $0.0063 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.

Related

limux CLAUDE.md compared with instructions from other repositories

limux CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
limux CLAUDE.mdam-will/limuxInstructions file5617d agoMITA1,587Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode