Codex QA

SkillAI & models

This skill lets your AI test and debug the omo Codex Light edition in a sandboxed environment. It runs the real Codex app against an isolated setup with a local mock model, so testing happens without real API calls and your actual Codex files are never touched.

Available today. Use it from your connected AI after setup.

Add the skill, then ask your AI to run a test of the omo Codex Light edition. It will work inside the sandbox and leave your real Codex setup alone.

Then ask your AI: use the Codex QA skill

What your AI can do with it

  • Test the omo Codex Light edition in a sandbox
  • Debug the Codex Light edition without touching your real Codex setup
  • Run the real Codex app against an isolated Codex home
  • Test with a local mock model so no real API calls are made
  • Confirm that only the Codex Light edition is exercised during tests

What this skill tells your AI

The instructions your AI receives, as published by code-yeongyu/oh-my-openagent in .agents/skills/codex-qa/SKILL.md and read by ahel’s review.

QA the omo Codex Light edition (packages/omo-codex/, shipped as lazycodex). We exercise OUR plugin in a REAL Codex while touching nothing of the user's setup: an isolated CODEX_HOME + a local mock model means no real API call and the real ~/.codex is never read or written. Each helper script ships a --self-test that asserts its scenario against the live machine, so the scripts are both the QA tools and their own regression checks.

Verified against codex-cli 0.140.0 (node, jq, tmux, bun on macOS). Confirm with codex --version; check a flag with codex <cmd> --help.

Golden rules (read before running anything)

  • QA ONLY our plugin. Everything that spawns codex uses an isolated CODEX_HOME (created by cqa_mk_isolated_home) and a LOCAL mock model provider (cqa_start_mock). Never QA against the real ~/.codex, never hit a real model API. The bundled scripts enforce this; if you run codex by hand, export CODEX_HOME="$(mktemp -d)/codex"; mkdir -p "$CODEX_HOME" FIRST (a set CODEX_HOME must already exist or codex hard-errors).
  • Prove the real home stayed clean. Every script shasums ~/.codex/config.toml before and after and asserts it is unchanged. If you script by hand, do the same.
  • The interactive codex is a shell function that injects --profile quotio. Bash scripts bypass it and get the real binary; never rely on the interactive alias. See references/isolation.md.
  • The first-party way to prove a hook fired is the app-server notification stream (hook/started / hook/completed), not log scraping. See references/app-server.md.
  • The captured JSON / pane IS the evidence — write it under .omo/evidence/<YYYYMMDD>-<slug>/ (no evidence file == the QA did not happen).

Setup

cd <this-skill-dir>                        # .agents/skills/codex-qa
bash scripts/lib/common.sh --self-check    # confirm deps + isolation harness

Docker is the default QA surface. Run this QA inside a disposable container that has the latest codex and a copy of your config, with the host ~/.codex untouched: script/agent/qa-docker.sh (see references/docker-qa.md). The local scripts below are the fallback for when Docker is unavailable or on Windows.

Router: pick your case

You need to…RunDeep dive
Prove a plugin hook fires in a LIVE Codex turn (first-party)scripts/app-server-drive.sh --pluginapp-server.md
Prove the app-server driver itself works (no plugin, fast)scripts/app-server-drive.sh --self-testapp-server.md
Install the LOCAL build into an isolated home + assert it landedscripts/install-verify.sh --self-testinstall-verify.md
Pin ONE component's hook logic deterministically (no codex)scripts/hook-unit-probe.sh --self-testcomponents-hooks.md
Smoke the real TUI under tmux (boots, renders, survives)scripts/tui-smoke.sh --self-testlogging-debug.md
Watch runtime logs while QAing(see reference; RUST_LOG / logs DB / /debug-config)logging-debug.md

Scripts index (each is its own regression test)

Script--self-test asserts
scripts/lib/common.sh --self-checkdeps present; isolated CODEX_HOME is created inside a sandbox and auto-removed on exit; mock model serves the Responses SSE; real ~/.codex unchanged
scripts/app-server-drive.sh--self-test: a bare turn completes and the mock assistant text comes back. --plugin: installs local omo, drives a turn, and asserts hook/completed for sessionStart,userPromptSubmit
scripts/install-verify.shlocal omo installs into the isolated home; config.toml enables omo@sisyphuslabs; component bins + agent TOMLs linked in the sandbox; real ~/.codex unchanged
scripts/hook-unit-probe.shthe ultrawork component injects <ultrawork-mode> on an ulw UserPromptSubmit (also a manual --component/--event mode)
scripts/tui-smoke.shthe real codex TUI boots in the isolated home, renders, and survives (no early exit); captures the pane

To tell a dev dogfood build apart from a published one on a REAL ~/.codex (NOT the isolated QA home), the repo ships bun run install:codex-dev, which stamps the plugin version as dev — visible as the (OmO dev) hook-status prefix every turn and as a [DEV] badge in omo get-local-version. Use it to confirm which build is loaded during manual dogfooding; it writes to the real home, so it is NEVER part of the isolated QA flow above.

When TUI visual QA evidence is needed, follow docs/reference/web-terminal-visual-qa.md: render the TUI through the real xterm.js web terminal - NEVER the tmux capture-pane frame, which degrades color and CJK width:

node script/qa/web-terminal-visual-qa.mjs --title "Codex TUI QA" \
  --command "codex" --input "{Enter}" \
  --evidence-dir .omo/evidence/<slug>/codex-web-terminal

The helper runs a real pty, renders it in xterm.js under Chrome, and writes terminal.txt, terminal-ansi.txt, terminal.png (true color), and metadata.json (--from-file <capture.ansi> replays a saved raw stream). Use that artifact set for TUI visual QA; use app-server-drive.sh --plugin for assertion-grade hook behavior.

Match QA to your change scope

  • Component / hook logic (packages/omo-codex/plugin/components/*): hook-unit-probe.sh for the exact stdout, THEN app-server-drive.sh --plugin to prove the live wiring. See components-hooks.md.
  • Installer / config.toml (packages/omo-codex/src/install/*): install-verify.sh.
  • Anything that affects a live session (hooks, agents, MCP wiring): app-server-drive.sh --plugin, and tui-smoke.sh --plugin if the TUI path matters.

Capturing evidence

ev=".omo/evidence/$(date +%Y%m%d)-codex-qa-<slug>"; mkdir -p "$ev"
bash scripts/app-server-drive.sh --plugin > "$ev/app-server-drive.json" 2>&1
bash scripts/install-verify.sh --self-test > "$ev/install-verify.txt" 2>&1

On /debugging

There is no /debugging command in Codex. To observe a run: the app-server notification stream (above), RUST_LOG=debug on the app-server's stderr, the logs SQLite under $CODEX_HOME, the TUI's /debug-config, and the codex debug … subcommands. See logging-debug.md.

Signals

GitHub stars
69k
Forks
6k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
codex-qa
Source
github.com/code-yeongyu/oh-my-openagent