Borrowing it
Nothing to install: this file belongs to Thurbeen/thurbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Thurbeen/thurbox/main/.agents/skills/ui-review/SKILL.mdgit clone --depth 1 https://github.com/Thurbeen/thurboxWrote 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.
[](https://agentmods.dev/skills/thurbeen/thurbox/ui-review)<a href="https://agentmods.dev/skills/thurbeen/thurbox/ui-review"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thurbeen/thurbox/ui-review"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 37 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.1 | $0.00037 | $0.01141 |
| Opus 5.5 | $0.00015 | $0.00456 |
| Sonnet 5.5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
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.
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.
How it starts
The opening of the file, as written. The whole thing — 95 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 .agents/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.
What ships with it
3 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.
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 Changed · -53 lines 40dc732b070a
- 1mo ago Changed 0ab121bc86a8
- 1mo ago Changed 228f186bf63c
- 2mo ago First seen · 148 lines · 37 tokens per session scan A 504295348f2c
ui-review is a skill published in the GitHub repository Thurbeen/thurbox (115 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,141 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
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.
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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.