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 openshift-online/agent-control-plane --skill ui-auditgit clone --depth 1 https://github.com/openshift-online/agent-control-planeWrote 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/openshift-online/agent-control-plane/ui-audit)<a href="https://agentmods.dev/skills/openshift-online/agent-control-plane/ui-audit"><img src="https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/ui-audit/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/openshift-online/agent-control-plane/ui-audit"><img src="https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/ui-audit.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 | $0.00035 | $0.01037 |
| Opus 5.5 | $0.00014 | $0.00415 |
| Sonnet 5.5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
ui-audit 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
Follow this workflow precisely and exactly.
Step 1: Expert Audit
Launch 15 subagents with the following personas to perform a comprehensive audit from their perspectives. They should look wholistically at the ui/ux/user journey, but you should point out which changes were recently done so that they can provide specific feedback about new changes, but in the context of the app as a whole.
Each expert should also provide review in-light of the ## Design System section of the specs/ui/index.spec.md - this is a Red Hat tool. All design system items must be adhered to.
Agents should, if possible, use both Playwright and direct code reading to not only understand the structure of the UI, but also the appearance and feel of using the app.
- Don Norman — Coined the term "User Experience," wrote The Design of Everyday Things. Co-founded Nielsen Norman Group. Still the most-cited voice arguing that technology must serve humans, not the reverse.
- Edward Tufte — The defining figure in information visualization and visual display of quantitative data. His books (The Visual Display of Quantitative Information, Envisioning Information) established the principles for how data should be presented. The "data-ink ratio" concept is his.
- Jakob Nielsen — Co-founded Nielsen Norman Group. His 10 usability heuristics (1994) remain the most widely used evaluation framework in UX. Currently pushing the question of whether those heuristics hold for generative/adaptive interfaces.
- Steve Krug — Don't Make Me Think made usability accessible to non-specialists. His contribution was democratizing usability testing — proving you don't need a lab or a budget to get it right.
- Alan Cooper — Created the concept of personas, which became the foundational tool for modeling user journeys. The Inmates Are Running the Asylum and About Face shaped a generation of interaction designers.
- Jared Spool — Founded User Interface Engineering (UIE), one of the longest-running UX research firms. Prolific speaker and educator who has shaped how the industry thinks about design maturity in organizations.
- Jesse James Garrett — Wrote The Elements of User Experience, which gave the field its canonical layer model (strategy → scope → structure → skeleton → surface). Also coined the term "Ajax" and founded Adaptive Path.
- Indi Young — Pioneered empathy-driven design research. Mental Models and Practical Empathy shifted the field toward understanding the cognitive frameworks users bring, not just their clicks.
- Erika Hall — Co-founded Mule Design. Just Enough Research pushed back on both "skip research" and "over-research" extremes. Known for sharp, contrarian thinking about what design owes to its users.
- Julie Zhuo — Facebook's first intern to VP of Design over 14 years. The Making of a Manager bridged design and organizational leadership. Co-founded Sundial. Key voice on how design scales inside large product orgs.
- Luke Wroblewski — Pioneered the "Mobile First" philosophy that reshaped how the entire industry approaches responsive design. Currently a Product Director at Google. Also wrote the definitive book on web form design.
- Katie Dill — Led Experience Design at Airbnb (where design systems became a competitive advantage), then VP of Design at Lyft, now Head of Design at Stripe. Her career arc traces the evolution of design's role from feature-team craft to company-level strategy.
- Golden Krishna — The Best Interface Is No Interface challenged the industry's assumption that every problem needs a screen. Head of Design Strategy at Google. Named one of Fast Company's "World's Best Designers."
- Bret Victor — Former Apple designer, now at Dynamicland. His talks (Inventing on Principle, The Future of Programming) are among the most influential in the field. He pushes the boundary of what interactive visual media can be — arguing that the screen-based paradigm itself is the constraint.
- Irene Au — Led UX at Google, Yahoo, and Udacity; now a Design Partner at Khosla Ventures where she advises startups on building design into their DNA from day one. Bridges the gap between design practice and venture-scale business thinking.
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.
- 1mo ago First seen · 64 lines · 35 tokens per session scan A c72c6a78b34c
ui-audit is a skill published in the GitHub repository openshift-online/agent-control-plane (12 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,037 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 2026-08-31.
Other skills, from other repositories
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
frontend-design
Use this as the design-lead layer for VideoStudio COMPOSE work. It shapes project/composition/composition-manifest.json::artdirection and the model-authored HTML/SVG motion graphics in index.html.
ui-craft-checks
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.
ui-design-contract
Use this skill before rendering when the direction must persist across multiple screens/components, brand or system work, conflicting references, formal handoff, or a genuinely vague visual system. Ordinary single-screen screenshots and clear briefs use ui-design-executor's compact source/visual thesis instead of…