A review tool for the thurbox text-based interface (TUI), which is an interface made of text panels in a terminal. It captures each main screen and panel, then produces an HTML report with visual and usability feedback.

Use it to build thurbox in an isolated temporary environment, capture screenshots of its screens and panels, and review the resulting HTML report. It can use a stub agent when no real agent command-line tools are installed.

It gives you a repeatable way to inspect the interface without disturbing real sessions, agent accounts, or the tmux server. It also provides a written record of issues across the screens.

ui-review — Skill for Claude Code and Codex by Thurbeen: A review tool for the thurbox text-based interface (TUI)…

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/thurbeen/thurbox/ui-review

Any agent

npx skills add Thurbeen/thurbox --skill ui-review

Clone the repo

git clone --depth 1 https://github.com/Thurbeen/thurbox

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-review.svg)](https://agentmods.dev/skills/thurbeen/thurbox/ui-review)

Your own site

<a href="https://agentmods.dev/skills/thurbeen/thurbox/ui-review"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,812 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.

Model	Per session	Once invoked
Fable 5	$0.00037	$0.01812
Opus 5	$0.00018	$0.00906
Sonnet 5	$0.00007	$0.00362
Haiku 4.5	$0.00004	$0.00181

Measured 5d ago against content hash 504295348f2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-review 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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_report.py, scripts/capture.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ui-review/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ui-review — screenshot the thurbox TUI and critique its UI/UX

This skill drives the real thurbox TUI inside an isolated, throwaway environment, takes a PNG screenshot of each major screen/panel, then has Claude look at every screenshot and write a self-contained HTML report with UI/UX feedback.

It reuses the proven isolation + seeding model from scripts/demo/record.sh, but swaps VHS video output for VHS Screenshot directives. Nothing it does touches your real thurbox sessions, tmux server, or agent accounts — everything runs against the thurbox-dev dev build in a mktemp sandbox that is torn down on exit.

Run this from the thurbox repo root (or any subdir of it). The output lands in target/ui-review/ (git-ignored).

Requirements

vhs (+ ffmpeg + ttyd), sqlite3, cargo, git, tmux. The capture script preflights these and fails fast with a clear message if any are missing. Real agent CLIs (claude/codex/antigravity/opencode) are optional — if none are installed the script registers a stub agent so every panel still renders.

Phase 1 — Capture

Resolve the skill directory and run the capture script. It builds the dev binaries, sets up the sandbox, seeds sessions/tasks/an automation, and runs VHS to emit one PNG per UI state plus a manifest.json describing them.

SKILL_DIR="$(cd "$(dirname "$(readlink -f .claude/skills/ui-review/SKILL.md)")" && pwd)"
# Default output dir is <repo>/target/ui-review/screenshots. Override with arg 1.
# Optional flags: --theme <thurbox-theme> (default doom), --width N, --height N.
"$SKILL_DIR/scripts/capture.sh"

When the user names a specific theme to review (e.g. "review the Tokyo Night theme"), pass --theme "Tokyo Night". Valid theme strings are the ones from Ctrl+Y in the TUI (e.g. doom, Catppuccin Mocha, Tokyo Night, Gruvbox Dark, Catppuccin Latte, …).

On success the script prints the screenshots dir and writes <dir>/manifest.json — a JSON array of {file, label, screen, keys} objects. Read it to learn what each PNG depicts.

Read the full file on GitHub · 148 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 148 lines · 37 tokens per session scan A 504295348f2c

Subscribe to this mod's changes

ui-review is a skill published in the GitHub repository Thurbeen/thurbox (60 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,812 once invoked, about $0.0002 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.

Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

ui-review