agentmods.dev

limux: Instructions file for Codex

AGENTS.md

limux AGENTS.md is an instructions file for Codex, OpenCode from am-will/limux. It costs 1,208 tokens per session, scanned A, original, MIT.

A contributor guide for Limux, a Linux desktop application for managing terminal workspaces. It describes the application’s Rust components, embedded terminal, command-line tool, and quality checks.

In plain words
What is it for?
Use it when modifying Limux’s GTK interface, terminal integration, Unix-socket control, command dispatcher, protocol types, CLI, or related Rust crates.
Why use it?
It helps agents understand which part of the project owns a feature and avoids confusing the contributor guide with a runtime-generated agent protocol file. This makes code changes and verification more targeted.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is am-will/limux's own configuration. It tells Codex and OpenCode 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 →

not rated 561repo +1 7d ago A scan 1,208 tokens original MIT
View source ↗ am-will/limux
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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/am-will/limux

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/am-will/limux/agents-md/github.svg)](https://agentmods.dev/instructions/am-will/limux/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/am-will/limux/agents-md"><img src="https://agentmods.dev/badge/instructions/am-will/limux/agents-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 AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/am-will/limux/agents-md"><img src="https://agentmods.dev/badge/instructions/am-will/limux/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,208 This file is loaded in full into every session.
When invoked 1,208 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 $0.01208 $0.01208
Opus 5.5 $0.00483 $0.00483
Sonnet 5.5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 2mo ago against content hash 6b134e1f87bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

limux AGENTS.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.

AGENTS.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Limux contributor guide

This file is for agents editing the Limux source tree. Do not confuse it with the AGENTS.md generated by limux agent-team inside a user's shared cwd; that generated file documents the runtime agent message protocol.

What Limux Is

Limux is a GTK4 + libadwaita terminal workspace manager for Linux. Terminal rendering is embedded Ghostty (libghostty.so), and external automation drives the running app through a Unix socket and the limux-cli crate.

Crates

Crate Role
limux-protocol JSON request/response envelope types.
limux-core In-process command dispatcher and state engine. Core IDs are u64.
limux-control Unix socket path, auth, framing, and standalone control server.
limux-ghostty-sys Raw FFI bindings to ghostty/include/ghostty.h.
limux-host-linux GTK host binary, window/pane/tab UI, terminal integration, live control bridge.
limux-cli User-facing CLI and agent integration commands.

Binaries

Local debug builds produce two important binaries:

  • target/debug/limux is the GTK host from limux-host-linux; it only accepts GTK/GApplication flags.
  • target/debug/limux-cli is the CLI; use this for subcommands such as identify, agent-team, notify, read-screen, and send.

Installed packages expose limux as the CLI. Running installed limux with no arguments launches the private host binary (limux-host) from libexec.

cargo build -p limux-cli --bin limux-cli
./target/debug/limux-cli --help

Quality Gate

The canonical check is:

./scripts/check.sh

It runs cargo fmt --check, cargo clippy --workspace --all-targets -- -D warnings, and cargo test --workspace. Run narrower checks while iterating:

cargo check -p limux-host-linux
cargo test -p limux-cli
cargo check --workspace

For live agent/control-socket behavior, prefer the maintained smoke harness:

./scripts/xvfb-smoke-test.sh
LIMUX_SMOKE_PROFILE=debug ./scripts/xvfb-smoke-test.sh

Read the full file on GitHub · 139 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. 2mo ago First seen · 139 lines · 1,208 tokens per session scan A 6b134e1f87bd

Subscribe to this mod's changes

limux AGENTS.md is an instructions file published in the GitHub repository am-will/limux (561 stars, last pushed 7d ago), licensed MIT. It adds 1,208 tokens to every session, about $0.0048 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.

LanguagesRust
Related

limux AGENTS.md compared with instructions from other repositories

limux AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
limux AGENTS.mdam-will/limuxInstructions file5617d agoMITA1,208Codex, OpenCode
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