Agent skill

Codex Plugin QA

by code-yeongyu in code-yeongyu/oh-my-openagent

Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

Custom licenceAuto-check passedTesting & QA

Install Codex Plugin QA

skills CLI
$ npx skills add code-yeongyu/oh-my-openagent --skill codex-qa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install code-yeongyu/oh-my-openagent codex-qa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codex-qa .claude/skills/codex-qa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-qa
GitHub stars
70k
Used in
1 other repo
Token cost
~1.9k tokens
SKILL.md length
768 words
Files
16 (incl. scripts, references)
Skills in repo
45
Repo updated
First seen
Licence
Custom licence

At a glance

Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

  • Changing anything under packages/omo-codex and needing to confirm it still works
  • SKILL.md covers Golden rules (read before…, Setup, Router: pick your case and Scripts index (each is its own…, plus 3 more sections
  • Runs Shell and JavaScript scripts from its folder; calls bash, codex and node
  • Proving that a Codex plugin hook really fired

What it does

The skill covers QA of the omo Codex Light edition (packages/omo-codex, shipped as lazycodex). Everything runs against a real Codex with a temporary CODEX_HOME and a local mock model provider, so no real model API is called and your own ~/.codex is neither read nor written. Each script checksums config.toml before and after to show that it stayed unchanged.

The main method drives codex app-server and asserts that hook/started and hook/completed notifications arrive, which counts as proof that a plugin hook fired, in place of log scraping. Other scripts verify an isolated install, probe individual hooks, run a tmux smoke test of the terminal UI and an LSP end-to-end check, and every helper ships a --self-test. References cover isolation, logging and debugging with RUST_LOG, and a Docker route that is the default QA surface, with local scripts as the fallback.

Captured JSON and pane output are saved as evidence under .omo/evidence in a dated folder that stays gitignored, while the pull request carries the summary. The scripts were verified against codex-cli 0.140.0 with node, jq, tmux and bun on macOS.

When your agent uses it

  • Changing anything under packages/omo-codex and needing to confirm it still works
  • Proving that a Codex plugin hook really fired
  • Verifying installer and config.toml output without touching a real Codex setup
  • Smoke-testing the Codex terminal UI in tmux

Example prompts

  • “I edited a hook under packages/omo-codex. Prove it still fires using the isolated app-server flow.”
  • “Run the install verification in a throwaway CODEX_HOME and confirm my real config.toml is unchanged.”
  • “Smoke-test the Codex TUI in tmux and save the pane capture as evidence.”
  • “Turn on RUST_LOG for the plugin run and tell me what the log shows.”

Requirements

  • The codex CLI
  • node, jq, tmux and bun
  • Docker for the default QA route

What it can do on your machine

Read from SKILL.md and the folder at commit ab81169. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (Shell and JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • codex
    • node
    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Plugin QA loads about 1.9k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 244 tokens; SKILL.md has 768 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~244
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 768 words (~1,948 tokens).

“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…”

— opening of SKILL.md by code-yeongyu, Custom licence
name
codex-qa

Read the full SKILL.md on GitHub

Files

SKILL.md and 15 other files (scripts, references) in .agents/skills/codex-qa of code-yeongyu/oh-my-openagent.

  • SKILL.md
  • references/app-server.md
  • references/components-hooks.md
  • references/docker-qa.md
  • references/install-verify.md
  • references/isolation.md
  • references/logging-debug.md
  • scripts/app-server-drive.sh
  • scripts/hook-unit-probe.sh
  • scripts/install-verify.sh
  • scripts/lib/app-server-client.mjs
  • scripts/lib/app-server-client.test.js
  • scripts/lib/common.sh
  • scripts/lib/mock-model.mjs
  • scripts/lsp-e2e.sh
  • scripts/tui-smoke.sh

Open the folder on GitHubat commit ab81169

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in code-yeongyu/oh-my-openagent, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Codex Plugin QA next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Plugin QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Plugin QA this skillcode-yeongyu/oh-my-openagent70k1 repos~1.9kAutomated safety check: PassCustom licence
Deck Reproasheshgoplani/agent-deck1k—~1.3kAutomated safety check: PassMIT
TUI Change Verification for Warpwarpdotdev/warp65k1 repos~5.5kAutomated safety check: NotesAGPL-3.0
DeerFlow Smoke Testbytedance/deer-flow83k—~2.5kAutomated safety check: NotesMIT
CodexBar Live QAsteipete/CodexBar22k—~1.2kAutomated safety check: PassMIT
Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness1.7k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Deck Repro

    asheshgoplani/agent-deck

    Reproduce agent-deck bugs from an issue, transcript excerpt, or description in an isolated environment, and prove fixes with the same reproduction and a regression test.

    1k GitHub stars~1.3k tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • Runs Warp's terminal UI for real, drives it with keystrokes and reads the rendered screen back to confirm that a change looks and behaves as intended.

    65k GitHub starsUsed in 1 repo~5.5k tokens
    Testing & QAAuto-check: notes
  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes
  • CodexBar Live QA

    steipete/CodexBar

    Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.

    22k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Weavebench Cua Reproduce

    AMAP-ML/LongHorizon-Harness

    Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.

    1.7k GitHub stars~1.6k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Senpi Agent QA Harness

    code-yeongyu/senpi

    Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.

    472 GitHub stars~2.7k tokensUpdated today
    Testing & QAAuto-check: notes

More from code-yeongyu/oh-my-openagent

All 45 skills in this repo
  • Browser Control with Omowright

    code-yeongyu/oh-my-openagent

    Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.

    70k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub starsUsed in 1 repo~2.8k tokens
    Auto-check passed
  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • LSP Setup

    code-yeongyu/oh-my-openagent

    Detects which languages a project uses, installs the matching language server, writes its config and checks it with a real call so diagnostics and go-to-definition work.

    70k GitHub stars~1.4k tokensUpdated today
    Auto-check: notes
  • OpenCode QA Toolkit

    code-yeongyu/oh-my-openagent

    Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.

    70k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • ULW Plan Workflow

    code-yeongyu/oh-my-openagent

    Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker.

    70k GitHub stars~3.9k tokensUpdated today
    Auto-check passed

Works with

Questions about Codex Plugin QA

What does Codex Plugin QA do?

Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex. The skill covers QA of the omo Codex Light edition (packages/omo-codex, shipped as lazycodex).codex is neither read nor written.

When should I use Codex Plugin QA?

Codex Plugin QA fits situations like: changing anything under packages/omo-codex and needing to confirm it still works; proving that a Codex plugin hook really fired; verifying installer and config.toml output without touching a real Codex setup; smoke-testing the Codex terminal UI in tmux.

How do I install Codex Plugin QA in Claude Code?

Run `npx skills add code-yeongyu/oh-my-openagent --skill codex-qa -a claude-code`. Or copy the skill folder (.agents/skills/codex-qa in code-yeongyu/oh-my-openagent) into .claude/skills/codex-qa in your project. Claude Code loads it when a task matches its description.

How do I install Codex Plugin QA in Codex?

Run `npx skills add code-yeongyu/oh-my-openagent --skill codex-qa -a codex`. Or copy the skill folder (.agents/skills/codex-qa in code-yeongyu/oh-my-openagent) into .agents/skills/codex-qa in your project. Codex loads it when a task matches its description.

Can I use Codex Plugin QA in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add code-yeongyu/oh-my-openagent --skill codex-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-qa, .gemini/skills/codex-qa, .github/skills/codex-qa and .opencode/skills/codex-qa in your project.

What does Codex Plugin QA need to run?

Going by SKILL.md and its folder, Codex Plugin QA needs a shell and JavaScript for the scripts in its folder and the command-line tools its instructions call (bash, codex, node and bun). Our summary lists: The codex CLI; node, jq, tmux and bun; Docker for the default QA route.

Does Codex Plugin QA access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Plugin QA safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codex Plugin QA use?

Codex Plugin QA has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Codex Plugin QA use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.1k tokens, read only when the agent opens those files.

What are the alternatives to Codex Plugin QA?

Skills that share tags, products or a category with Codex Plugin QA: Deck Repro (asheshgoplani/agent-deck, 1k stars), TUI Change Verification for Warp (warpdotdev/warp, 65k stars), DeerFlow Smoke Test (bytedance/deer-flow, 83k stars) and CodexBar Live QA (steipete/CodexBar, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Plugin QA?

code-yeongyu (a GitHub user) maintains it in code-yeongyu/oh-my-openagent, which has 69,882 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on October 8, 2026.

Source: code-yeongyu/oh-my-openagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.