agentmods.dev

codex-desktop-linux AGENTS.md

Repository instructions for codex-desktop, a Linux distribution built from OpenAI's signed ChatGPT package. They cover supported computer architectures, package formats, signature checks, extraction rules, application identity, and desktop naming.

In plain words
What is it for?
Use them when updating the Linux package, verifying downloads, building deb, RPM, pacman, AppImage, or Nix outputs, or changing installation and branding behavior.
Why use it?
They protect the build from untrusted packages and accidental changes to the upstream application. They also keep the Linux packages clearly separate from the original distribution.

Instructions file for CodexOpenCode

3.7k +7 yesterday A scan 1,444 tokens original MIT
View the source file ilysenko/codex-desktop-linux
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/ilysenko/codex-desktop-linux/agents-md
Clone the repo
git clone --depth 1 https://github.com/ilysenko/codex-desktop-linux

Made for: Codex, OpenCode.

Per session 1,444 This file is loaded in full into every session.
When invoked 1,444 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 $0.01444 $0.01444
Opus 5 $0.00722 $0.00722
Sonnet 5 $0.00289 $0.00289
Haiku 4.5 $0.00144 $0.00144

Measured 3d ago against content hash b1d42c73f92a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-desktop-linux 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 3d 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This repository repackages OpenAI's signed official Linux chatgpt package as the independently named codex-desktop distribution. It preserves the official ELF/Electron payload and bundled tools, adds disabled-by-default Linux features, builds deb/RPM/pacman/AppImage/Nix outputs, and ships a Rust update manager that rebuilds from the signed stable APT repository.

Non-negotiable rules

  • Support only the latest signed stable OpenAI Linux package on amd64 and arm64. Remove obsolete drift paths in the same change.
  • Trust InRelease through the pinned repository key, then verify Packages and package SHA-256 values. latest URLs are never a trust root.
  • Never execute upstream maintainer scripts. Extract the data payload only.
  • A clean build with no enabled ASAR feature must preserve resources/app.asar byte-for-byte.
  • Keep the output identity codex-desktop under /opt/codex-desktop; do not install the upstream APT source, key, package identity, or maintainer scripts.
  • Keep the user-facing desktop name ChatGPT Community and its distinct community icon; ChatGPT without the qualifier identifies the upstream app.
  • The default core patch registry is empty. A core patch requires a reproduced launch/work blocker and a required regression test.
  • Experimental or workflow-specific behavior belongs in linux-features/ and remains disabled in committed configuration.
  • Known retired feature IDs are ignored; arbitrary unknown IDs remain errors.
  • Do not edit generated output (codex-app/, dist/, candidates, target/).

Source routing

  • Upstream verification/extraction: scripts/lib/upstream-linux-package.js and scripts/lib/upstream-linux-package.sh.
  • Build orchestration: install.sh, scripts/lib/*.sh.
  • Launcher: launcher/start.sh.template.
  • Feature descriptors/resources/hooks: linux-features/<id>/.
  • ASAR engine/reporting: scripts/patches/, scripts/patch-linux-window-ui.js, scripts/lib/patch-report.js.
  • Packaging: scripts/build-*.sh, scripts/lib/package-common.sh, packaging/.
  • Updater: updater/src/; minimal rebuild payload: packaging/update-builder/.
  • Signed-release automation: scripts/automation/upstream-linux-package-watchdog/.
  • Nix: flake.nix, nix/upstream-linux-packages.json, nix/*.nix.

Read the full file on GitHub · 141 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. 3d ago First seen · 141 lines · 1,444 tokens per session scan A b1d42c73f92a

Subscribe to this mod's changes

codex-desktop-linux AGENTS.md is an instructions file published in the GitHub repository ilysenko/codex-desktop-linux (3,744 stars, last pushed yesterday), licensed MIT. It adds 1,444 tokens to every session, about $0.0072 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.

DevOps and cloudSecurityai-codingappimagearchlinuxcodexcodex-desktopdebian
Related

Other instructions, from other repositories

codex-command-center AGENTS.md

Instructions for sevensir888/codex-command-center, a project described as: A local desktop control center for organizing Codex projects, engineering tasks, sessions, Git changes, Skills, and MCP configuration.

sevensir888/codex-command-center · 556 tokens

TechShorts AGENTS.md

AGENTS.md instructions for LarsenCodeLabs/TechShorts, covering repository structure, core product constraints, development and verification, security and configuration and solana/anchor protocol rules.

LarsenCodeLabs/TechShorts · 850 tokens

project-os-for-codex AGENTS.md

Instructions for herry2059/project-os-for-codex, covering ai contributor rules, product truth, architecture and security, development workflow and agent integration contract.

herry2059/project-os-for-codex · 656 tokens

AmbyKit CLAUDE.md

Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.

ambystechcom/AmbyKit · 257 tokens

sugar AGENTS.md

AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.

roboticforce/sugar · 1,551 tokens

nextjs-skills CLAUDE.md

Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.

mohamed-hossam1/nextjs-skills · 69 tokens