codex-dev

A development workflow for quickly changing and testing a Linux version of the Codex desktop app. It can reload certain interface changes in about a second and connect to the running app for inspection.

In plain words
What is it for?
Editing JavaScript patches or launcher files, reloading the running app, inspecting its page, network activity, and console, and driving selected app actions.
Why use it?
It avoids waiting for the full installation rebuild during repeated code changes.

Skill for Claude CodeCodex

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 skills/distsystem/codex-desktop-linux/codex-dev
Any agent
npx skills add distsystem/codex-desktop-linux --skill codex-dev
Clone the repo
git clone --depth 1 https://github.com/distsystem/codex-desktop-linux

Made for: Claude Code, Codex.

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,221 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00134 $0.02221
Opus 5 $0.00067 $0.01111
Sonnet 5 $0.00027 $0.00444
Haiku 4.5 $0.00013 $0.00222

Measured yesterday against content hash 983f191e1c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-dev 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 yesterday.

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/skills/codex-dev/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Dev Workflow

Fast-loop primitives for iterating on the Linux fork's patches and launcher without paying ./install.sh's 2-minute rebuild cost.

When to Use This

Use when working in this repo and you want to:

  • See a scripts/patches/*.js change reflected in the running codex within ~1 second (renderer SSE reload)
  • Edit launcher/start.sh.template and re-run codex against it directly (no install.sh regeneration)
  • Drive the running codex programmatically (CDP attach for DOM/Network/ Console inspection, or IPC-level actions like toggling the avatar overlay)

Do NOT use for: production install workflows (./install.sh, AUR/.deb/ .rpm builds), codex-app-next/ rebuild candidate flow.

Quick Reference

./scripts/dev.sh                    launch codex against codex-app/ with
                                    CODEX_LINUX_DEV_RELOAD + DEV_TOOLS on
                                    (CDP @ :9333, SSE reload @ :5175)

./scripts/dev-hot-patch.sh          re-apply scripts/patches/*.js + rsync
                                    webview tree + POST /dev/notify-reload
                                    → renderer reloads in ~1s
                                    auto-seeds asar baseline on first run

./scripts/dev-mascot.sh [open|close|toggle]
                                    drive avatar overlay via CDP IPC dispatch
                                    (sendMessageFromView avatar-overlay-open)

./scripts/dev-tray-mock.sh [N|clear]
                                    DOM-inject N fake tray cards + size IPC
                                    (eyeball only — bypasses React data flow)

Architecture

   install.sh pipeline stages we slice into:

   ┌──── extract DMG → patch asar → electron rebuild → install ────┐
   │       (5s)        (5s)         (60s)              (5s)         │
   │                    │                                            │
   │                    ▼                                            │
   │              dev-hot-patch.sh re-runs JUST THE PATCHER         │
   │              against the cached baseline, rsyncs webview/,     │
   │              POSTs reload → ~1s end-to-end                     │
   │                                                                 │
   └──── render launcher (start.sh) from launcher/start.sh.template ┘
                                    │
                                    ▼
                              dev.sh execs the template DIRECTLY
                              (skip install.sh's create_start_script),
                              so template edits are live

Read the full file on GitHub · 221 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. yesterday First seen · 221 lines · 134 tokens per session scan A 983f191e1c04

Subscribe to this mod's changes

codex-dev is a skill published in the GitHub repository distsystem/codex-desktop-linux (11 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 2,221 once invoked, about $0.0007 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens