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 BlackBeltTechnology/pi-agent-dashboard --skill frontend-mockup-loopgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/frontend-mockup-loop)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/frontend-mockup-loop"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/frontend-mockup-loop/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/blackbelttechnology/pi-agent-dashboard/frontend-mockup-loop"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/frontend-mockup-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00185 | $0.02941 |
| Opus 5 | $0.00093 | $0.01470 |
| Sonnet 5 | $0.00037 | $0.00588 |
| Haiku 4.5 | $0.00018 | $0.00294 |
Grade A, and why
frontend-mockup-loop 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
frontend-mockup-loop
A disciplined loop for designing frontend surfaces. It exists to defeat distributional convergence: an undirected agent regresses to the statistical mean of its training data — generic Inter font, a purple gradient, a centered hero. "Make it look better" just returns the average again.
The fix the whole agentic-design field converged on, and what this loop enforces every time:
- deliberate direction from a real reference (GROUND),
- a consistent token system (the ui-contract),
- a screenshot feedback loop (eyes on output).
This skill is paired with an extension that registers five tools:
serve_mockup, score_mockup, init_ui_contract, list_design_systems,
validate_mockup.
Select a design system (optional)
The loop runs design-system agnostic by default (generic anti-slop rubric).
To target a specific system, pick a preset and pass its id to the tools'
system param. v1 presets (list_design_systems enumerates them):
| id | system | platform | substrate |
|---|---|---|---|
shadcn |
shadcn/ui + Tailwind | web | HTML + Tailwind |
mui |
Material UI | web | HTML |
material-3 |
Material Design 3 | web | HTML |
fluent-2 |
Fluent 2 | web | HTML |
apple-hig |
Apple HIG | iOS | HTML approximation → SwiftUI on promote |
With a system selected: init_ui_contract{system} writes that system's DTCG
token contract (from a bundled, offline snapshot; refresh:true re-fetches
upstream), score_mockup{system} swaps in the system's boolean rubric, and
validate_mockup{system,dir} runs the gated pipeline.
Gate vs advisory
Validation is layered. Gates block pass; advisory layers only score
and drive the fix loop (LLM visual scores skew positive — never hard-block):
- L1 token-lint — static; HARD GATE when a linter applies (off-token color literals fail shadcn/material-3).
- L2 a11y floor — rendered axe + WCAG contrast; HARD GATE, every system.
- L3 named-system auditor —
hig-doctor/material3-mcpetc., advisory, shelled out only if installed (absent → skipped + noted, never errors). - L4 vision rubric — per-preset boolean checks;
score = pass/Ncomputed in code, advisory.
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 · 220 lines · 185 tokens per session scan A bebcca20e2c5
frontend-mockup-loop is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (278 stars, last pushed today), licensed MIT. It adds 185 tokens to every session and 2,941 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
adaptive-interfaces
Use when designing for user preferences — motion sensitivity, contrast needs, colour schemes, text sizing, information density, or any interface behaviour that should adapt to individual needs.
responsive-patterns
Use when designing complex responsive layouts — breakpoint strategy, layout shifts, content reflow, responsive typography, container queries, and ensuring the experience works across the full device spectrum.
token-architecture
Use when building or restructuring design token systems — global tokens, semantic tokens, component tokens, naming conventions, theming, and multi-platform token distribution.
ui-composition
Use when building layouts, choosing colours, setting typography, establishing visual hierarchy, designing responsive behaviour, or making any visual design decision — ensures every visual choice serves both aesthetics and accessibility.
motion-choreography
Use when designing animation sequences, page transitions, micro-interactions, loading states, or any motion that communicates meaning — ensures motion is purposeful, performant, and safe for motion-sensitive users.
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.