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 TimboGP/timbogp-marketplace --skill ux-onboardinggit clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/timbogp/timbogp-marketplace/ux-onboarding)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/ux-onboarding"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/ux-onboarding/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/timbogp/timbogp-marketplace/ux-onboarding"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/ux-onboarding.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00145 | $0.00985 |
| Opus 5 | $0.00072 | $0.00492 |
| Sonnet 5 | $0.00029 | $0.00197 |
| Haiku 4.5 | $0.00015 | $0.00098 |
Grade A, and why
ux-onboarding 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 12d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Onboarding
Build a working mental model of how this project does UX — its design tokens, component patterns, accessibility conventions, interaction-feedback states, and copy voice — by being walked through the real code, not by reading a summary. This is familiarization, not scaffolding (the ux-foundations skill / /ux-bootstrap) or scoring (the ux-audit skill / /ux-audit). Lean on the ux-foundations, design-tokens, accessible-components, interaction-feedback, and ux-audit skills for what "good" looks like in each area.
When to use
The user wants to understand an existing UX/design layer they did not build — joining a new repo, picking up an unfamiliar frontend, or learning a team's conventions. Phrases like "walk me through this app's UX", "onboard me onto the design system", or "explain how this project handles components/tokens/a11y". If they instead want to create a baseline, use ux-foundations; to score one, use ux-audit.
Optional focus: a path or an area (e.g. "tokens", "the dialog component"). If none is given, cover the design layer end to end.
Procedure
- Detect the stack and survey the design layer. Read
../ux-foundations/references/stack-detection.mdand run it; report framework, styling approach, and language in one line. Then build a short map: where tokens/theme live, the component library and its primitives, styling conventions, the accessibility patterns in use, the interaction-feedback patterns (loading / empty / error / success, toasts), and copy/voice conventions. Skim recent history (git log, recently merged PRs) for changes to use in step 4. - Confirm the path. List the parts you'll walk through — dependencies first, usually tokens → primitives → composed components → app screens — and confirm scope. Honor any focus the user gave.
- Walk it part by part — one part at a time, never a wall of text. For each:
- Explain how this project handles it and the pattern/convention it follows.
- Send the user to the code — name concrete files/components to open and read (e.g. "open
tokens.cssandButton.tsx"), rather than pasting them. - Ask questions to answer — a few comprehension/prediction questions ("which token drives the focus-ring color?", "what makes this dialog's focus trap correct?"), then check the answers, correct misconceptions, and push deeper before moving on.
- Reimplement a recent change. From recent history, pick a few smaller UX/design changes — a new component variant, a token change, an added interaction state, a copy fix — each small enough to redo in one sitting and ideally in a part already walked. Present them as an interactive choice; the user picks one (or asks for different candidates). Stub out or revert it in a scratch copy (without showing the original diff), state the change's intent and acceptance criteria, and have the user reimplement it. Then review against what the project actually shipped — convention fit, accessibility, and which approach is better and why.
- Wrap up. Summarize the parts covered and the user's comprehension, the reimplementation outcome, and suggest the
ux-auditskill (to score what they now understand) or a focused component review as next steps.
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.
- 12d ago First seen · 33 lines · 145 tokens per session scan A 076a4145acbd
ux-onboarding is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 145 tokens to every session and 985 once invoked, about $0.0007 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
accessibility
Audits code for WCAG 2.2 AA compliance and provides design guidance for accessible components. Covers semantic HTML, ARIA, keyboard nav, contrast, focus management, and motion.
abd-design
ABD Design agent: produces architecture diagrams, component breakdowns, data flow, and design decisions from the current plan.
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
ux-review
Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.
art-bible
Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset production. Run after /brainstorm is approved and before /map-systems or any GDD authoring begins.
unity-ui-patterns
Unity UI/UX pattern design-to-code translation. Screen flow architecture, View/ViewModel separation, HUD architecture, feedback & juice systems, dynamic list/grid views, transition & animation contracts. UI Toolkit only. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.