New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Validate Tui In Codex

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence.

Apache-2.0Auto-check passedProductivity & Automation

Install Validate Tui In Codex

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill validate-tui-in-codex -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins validate-tui-in-codex --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/bnc4vk/codex-tui-proof/skills/validate-tui-in-codex .claude/skills/validate-tui-in-codex && 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
validate-tui-in-codex
GitHub stars
1.2k
Token cost
~1.5k tokens
SKILL.md length
705 words
Files
3 (incl. references)
Skills in repo
686
Repo updated
First seen
Licence
Apache-2.0

At a glance

Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence.

  • Works in 6 steps: Select the target → Start the proof runtime → Use Codex's browser → …
  • TUI layout changes
  • SKILL.md covers Hard boundary, 1. Select the target, 2. Start the proof runtime and 3. Use Codex's browser, plus 4 more sections
  • Calls node and npm

What it does

Validate Tui In Codex is an agent skill from hashgraph-online/awesome-codex-plugins. Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence. Use for TUI layout changes, terminal menus, colors, prompts, resize behavior, keyboard flows, or proof-of-work where Codex would otherwise reach for Computer Use or a desktop terminal. Do not use for desktop-terminal-emulator-specific behavior or ordinary non-interactive command output.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/evidence-contract.md`).

It sits in Productivity & Automation, covering Desktop control and Verification before completion. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • TUI layout changes
  • Resize behavior
  • Proof-of-work where Codex would otherwise reach for Computer Use
  • A desktop terminal

Example prompts

  • “/validate-tui-in-codex”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Select the target
  2. Start the proof runtime
  3. Use Codex's browser
  4. Validate behavior
  5. Capture and report proof
  6. Clean up

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. 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

    Shell commands in SKILL.md call:

    • node
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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

Validate Tui In Codex loads about 1.5k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 705 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 705 words, ~1,453 tokens.

Download SKILL.mdSave it as .claude/skills/validate-tui-in-codex/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
validate-tui-in-codex
description
Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence. Use for TUI layout changes, terminal menus, colors, prompts, resize behavior, keyboard flows, or proof-of-work where Codex would otherwise reach for Computer Use or a desktop terminal. Do not use for desktop-terminal-emulator-specific behavior or ordinary non-interactive command output.

Validate a TUI in Codex

Run the target in the bundled localhost harness, drive it through Codex's in-app browser, and attach visual evidence without controlling the user's desktop.

Hard boundary

  • Never invoke Computer Use, Terminal.app, iTerm, or desktop mouse/keyboard automation for this workflow.
  • Use only the integrated terminal execution surface and Codex's in-app browser.
  • If the in-app browser capability is unavailable, stop and report that limitation. Do not silently fall back to Computer Use.
  • Keep the server bound to 127.0.0.1.
  • Never type passwords, tokens, private keys, or other secrets into the proof terminal. Input and output are recorded locally as JSONL.

1. Select the target

Determine:

  • command: the real TUI command, including safe arguments;
  • cwd: the requested repository or worktree, defaulting to the current workspace;
  • geometry: default 100x30, changing it only when the task requires another fixed size;
  • interaction: the smallest keyboard flow that proves the requested behavior.

Do not send prompts that trigger paid or external actions unless the user authorized them. Prefer menus, navigation, local commands, and reversible state changes for visual proof.

The launcher parses the command into an executable and arguments without invoking a shell. Do not use pipes, redirects, command substitution, or environment assignments. Put complex setup into a reviewed script and launch that script.

2. Start the proof runtime

Resolve this skill's directory from the selected SKILL.md. The runner is two directories above it at scripts/tui-proof.mjs.

Run the doctor once when diagnosing setup:

sh
node <plugin-root>/scripts/tui-proof.mjs doctor

Doctor output is JSON. Require ok: true; when dependencies are not ready, starting the harness installs the three versions locked in runtime/package-lock.json with npm ci.

Start the harness from the target working directory in a persistent integrated-terminal session:

sh
node <plugin-root>/scripts/tui-proof.mjs start \
  --command "<command>" \
  --cwd "<absolute-worktree>" \
  --cols 100 \
  --rows 30 \
  --port 0

Wait for a line beginning with TUI_PROOF_READY. Parse its JSON and use the returned url; never guess the allocated port. The first run may install three local runtime dependencies.

3. Use Codex's browser

Use the available control-in-app-browser skill and follow its setup instructions completely. Select the in-app browser (iab), not the user's Chrome profile.

Open the exact localhost URL from TUI_PROOF_READY. After navigation:

  1. Inspect a fresh DOM snapshot.
  2. Confirm data-testid="status" reports running.
  3. Confirm data-testid="dimensions" matches the requested geometry.
  4. Confirm the visible session command and working directory are correct.
  5. Locate the unique textbox "Terminal input" before sending keys.

Use browser Playwright locators for keyboard interaction. Type literal text separately from Enter when submitting input. After every state-changing action, observe the smallest fresh DOM or visual state needed to confirm the result.

Show full SKILL.md (293 more words)Show less

4. Validate behavior

Exercise the requested path and collect both kinds of evidence:

  • Semantic evidence: DOM snapshot text, status, dimensions, and /api/evidence.
  • Visual evidence: an in-app-browser screenshot showing the relevant rendered TUI state.

For resize work, change the visible Cols/Rows controls and verify data-testid="dimensions" changes. Restore the requested deterministic geometry before the final screenshot unless the resized state is the subject of the proof.

For restart/stop work, use the visible buttons and verify the status transition. Do not infer success from a click alone.

Read references/evidence-contract.md when API fields, selectors, recording format, or acceptance criteria matter.

5. Capture and report proof

Take a screenshot from the controlled browser tab itself. Save it under the target repository, preferably:

text
artifacts/tui-proof/<descriptive-name>.png

Inspect the captured image before attaching it. If the target-tab capture is visibly incomplete while the DOM snapshot proves the page is intact, wait briefly and retry once; never substitute a desktop/current-window screenshot.

Attach the image inline in the final response using its absolute local path. Also query GET /api/evidence and report:

  • command and cwd;
  • terminal geometry;
  • observed interaction and resulting state;
  • session status and recording path;
  • whether browser logs contained errors.

Explicitly state that the validation used the Codex in-app browser and did not use Computer Use.

6. Clean up

Keep the harness running only while useful for iteration. When the task is complete and the user did not ask to keep it open:

  1. Stop the session through the browser control.
  2. Terminate the persistent integrated-terminal server session.
  3. Preserve requested screenshots and JSONL evidence.

Limits

This validates a real PTY rendered by xterm.js. It does not prove behavior unique to Terminal.app, iTerm, Kitty, OS permission dialogs, native clipboard integration, or a specific terminal renderer. Escalate those cases explicitly instead of overstating the proof.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in plugins/bnc4vk/codex-tui-proof/skills/validate-tui-in-codex of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • agents/openai.yaml
  • references/evidence-contract.md

Open the folder on GitHubat commit 78497e5

Compare with similar skills

Validate Tui In Codex 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.

Validate Tui In Codex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Validate Tui In Codex this skillhashgraph-online/awesome-codex-plugins1.2k—~1.5kAutomated safety check: PassApache-2.0
Evidence-Driven Testingmichaelshimeles/skills1.3k1 repos~3.9kAutomated safety check: PassNone
Vision SkillsAnionex/agent-vision-toolkit1.2k1 repos~4kAutomated safety check: PassMIT
Mac Computer UseTo3akaRin/mac-computer-use1.1k1 repos~495Automated safety check: PassMIT
AtomicmailAtomic-Mail/atomic-mail-agentic2661 repos~2kAutomated safety check: PassMIT
Crabbox Appsopenclaw/openclaw392k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Evidence-Driven Testing

    michaelshimeles/skills

    Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.

    1.3k GitHub starsUsed in 1 repo~3.9k tokens
    Testing & QAAuto-check passed

  • Vision Skills

    Anionex/agent-vision-toolkit

    Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…

    1.2k GitHub starsUsed in 1 repo~4k tokens
    Productivity & AutomationAuto-check passed

  • Mac Computer Use

    To3akaRin/mac-computer-use

    操作 macOS 桌面应用，探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作，以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收；普通网页任务优先使用已有浏览器工具。

    1.1k GitHub starsUsed in 1 repo~495 tokens
    Productivity & AutomationAuto-check passed

  • Atomicmail

    Atomic-Mail/atomic-mail-agentic

    Read and write email through the Atomic Mail from an AI agent.

    266 GitHub starsUsed in 1 repo~2k tokens
    Productivity & AutomationAuto-check passed

  • Crabbox Apps

    openclaw/openclaw

    A skill your agent uses when asked to open, run, test, or show an app in Crabbox, including native desktops, web previews, and computer use on a temporary machine.

    392k GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Agent Management

    autonomous-ai/Physical-AI-Operating-System

    Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions.

    381 GitHub stars~1.7k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed

  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Categories

Questions about Validate Tui In Codex

What does Validate Tui In Codex do?

Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence. Validate Tui In Codex is an agent skill from hashgraph-online/awesome-codex-plugins. Visually validate an interactive CLI or terminal UI in Codex's in-app browser using a real local PTY, fixed rendering, keyboard interaction, screenshots, and session evidence.

When should I use Validate Tui In Codex?

Validate Tui In Codex fits situations like: TUI layout changes; resize behavior; proof-of-work where Codex would otherwise reach for Computer Use; A desktop terminal.

How do I install Validate Tui In Codex in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill validate-tui-in-codex -a claude-code`. Or copy the skill folder (plugins/bnc4vk/codex-tui-proof/skills/validate-tui-in-codex in hashgraph-online/awesome-codex-plugins) into .claude/skills/validate-tui-in-codex in your project. Claude Code loads it when a task matches its description.

How do I install Validate Tui In Codex in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill validate-tui-in-codex -a codex`. Or copy the skill folder (plugins/bnc4vk/codex-tui-proof/skills/validate-tui-in-codex in hashgraph-online/awesome-codex-plugins) into .agents/skills/validate-tui-in-codex in your project. Codex loads it when a task matches its description.

Can I use Validate Tui In Codex 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 hashgraph-online/awesome-codex-plugins --skill validate-tui-in-codex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validate-tui-in-codex, .gemini/skills/validate-tui-in-codex, .github/skills/validate-tui-in-codex and .opencode/skills/validate-tui-in-codex in your project.

What does Validate Tui In Codex need to run?

Going by SKILL.md and its folder, Validate Tui In Codex needs the command-line tools its instructions call (node and npm).

Does Validate Tui In Codex access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Validate Tui In Codex 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. Review the folder before installing.

What licence does Validate Tui In Codex use?

Validate Tui In Codex is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Validate Tui In Codex use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 620 tokens, read only when the agent opens those files.

What are the alternatives to Validate Tui In Codex?

Skills that share tags, products or a category with Validate Tui In Codex: Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars), Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars), Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars) and Atomicmail (Atomic-Mail/atomic-mail-agentic, 266 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Validate Tui In Codex?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.