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.
npx skills add mr-tbot/Auto-Everything --skill auto-ui-uxgit clone --depth 1 https://github.com/mr-tbot/Auto-EverythingWrote 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/mr-tbot/auto-everything/auto-ui-ux)<a href="https://agentmods.dev/skills/mr-tbot/auto-everything/auto-ui-ux"><img src="https://agentmods.dev/badge/skills/mr-tbot/auto-everything/auto-ui-ux.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00107 | $0.04497 |
| Opus 5 | $0.00053 | $0.02249 |
| Sonnet 5 | $0.00021 | $0.00899 |
| Haiku 4.5 | $0.00011 | $0.00450 |
Grade A, and why
auto-ui-ux 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 6d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-ui-ux
Bring a codebase's interface to a finished, coherent, professional state — correctness, completeness, and cohesion — and keep iterating until a full pass finds nothing.
The failure this exists for: a project built in phases, each phase by a different hand with a different idea of what the UI should be. Two button components, three greys that are nearly the same grey, one screen with empty states and five without. Nothing is broken enough to file, and the whole thing reads as unfinished.
Step 0 — Mode, Scope, Freeze
Pick a mode. Ask once, then commit:
- INTERACTIVE (default) — you ask before each decision that has taste in it: palette, type, assets, which idiom wins. Best when the user has opinions, brand assets, or a client.
- AUTO — you derive the target system from what is already in the codebase and align everything to it on your own judgment, asking nothing. Best for a backlog of drift, or an unattended pass. AUTO still reports every judgment call it made, and still stops for anything on the freeze list.
Establish the freeze list before touching anything: screens, components, or brand elements that must not change. Anything the user is proud of, anything a client signed off, anything with an established visual identity. Absent instruction, the freeze list includes the logo, brand colors, and any screen the user names.
Cohesion beats novelty. You are extending an existing design language, not inventing one. Small feature-driven tweaks are yours to make. A new design system, a font change, a palette change, or restyling components that already work is a proposal, not an action — even in AUTO mode.
Pass 1 — Inventory And Drift
Enumerate the whole surface before changing any of it: every screen/route/view, every component, and every entry point. Then extract every hardcoded design value:
# colors: hex, rgb/rgba, hsl, and platform literals
rg -n --no-heading -e '#[0-9a-fA-F]{3,8}\b' -e 'rgba?\(' -e 'hsla?\(' -e 'Color\(0x' -e 'UIColor\(' -e 'Color\.[a-z]'
# spacing, radius, shadow, z-index
rg -n -e '\b(margin|padding|gap|inset)[^:]*:\s*[0-9]' -e 'border-radius|cornerRadius|clipShape' -e 'box-shadow|elevation|shadowRadius' -e 'z-index'
# type
rg -n -e 'font-family|fontFamily|FontFamily|\.font\(' -e 'font-size|fontSize|textSize|\.sp\b|\.dp\b'
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.
- 6d ago First seen · 324 lines · 107 tokens per session scan A e1a8bbf8110f
auto-ui-ux is a skill published in the GitHub repository mr-tbot/Auto-Everything (7 stars, last pushed 5d ago), licensed MIT. It adds 107 tokens to every session and 4,497 once invoked, about $0.0005 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 2026-08-31.
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).
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.