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 labsai/EDDI --skill eddi-uigit clone --depth 1 https://github.com/labsai/EDDIWrote 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/labsai/eddi/eddi-ui)<a href="https://agentmods.dev/skills/labsai/eddi/eddi-ui"><img src="https://agentmods.dev/badge/skills/labsai/eddi/eddi-ui/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/labsai/eddi/eddi-ui"><img src="https://agentmods.dev/badge/skills/labsai/eddi/eddi-ui.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 | $0.00040 | $0.02512 |
| Opus 5.5 | $0.00016 | $0.01005 |
| Sonnet 5.5 | $0.00008 | $0.00502 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
eddi-ui 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 16d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EDDI Manager UI
Black & gold admin dashboard. React 19 + Tailwind CSS v4 + CSS-variable tokens. Style with Tailwind utilities that read tokens. Never hand-write CSS, never invent a class system, never use raw hex.
What already exists — import it
src/components/ui/ — primitives
| Component | Notes |
|---|---|
Button |
variant: primary (default) · secondary · destructive · warning · outline · ghost · link. size: sm · md (default) · lg · icon. asChild for link buttons. Lucide icon as a child auto-sizes to 16px. |
Badge |
variant: default (gold) · secondary · success · warning · destructive · outline. Pill, text-xs font-semibold. |
Card |
Compose Card > CardHeader (CardTitle, CardDescription) + CardContent + CardFooter. rounded-xl border bg-card shadow-sm; header is p-5 pb-0, content p-5. |
Input |
h-10 rounded-lg, gold focus ring. Plain InputHTMLAttributes. |
Skeleton |
Loading placeholder. |
AccessibleDialog |
Focus-trapped modal. |
AlertDialog |
Confirm/destructive prompt: open, onOpenChange, title, description, onConfirm, confirmLabel, cancelLabel, isPending, variant (destructive | warning), plus children for extra controls between description and buttons (e.g. a "permanently delete" checkbox). Use for every delete. |
UnsavedChangesDialog |
Discard-changes confirm. Pair with useUnsavedChangesGuard. |
DropdownMenu |
Radix wrapper. |
ErrorBoundary |
Wrap risky subtrees. |
StreamBadge |
Live/streaming indicator. |
ResizeHandle |
Draggable, keyboard-operable separator between panels: direction, label, onResize(delta) — the delta is logical (positive = this panel grows), so it is RTL-safe. value/min/max let it report its position. |
src/components/shared/ — app-level
| Component | Use it for |
|---|---|
EmptyState |
icon (Lucide), title, description?, actionLabel?, onAction?. Dashed-border box, py-16. |
ErrorState |
message, onRetry?, retryLabel?. Destructive-tinted box. |
ViewToggle |
Card ↔ list switch. Already keyboard-accessible (arrow keys, radiogroup). |
BackLink |
Detail-page back nav. Takes only to / label — no className. |
AgentPicker, SecretKeyPicker |
Async pickers, already wired to react-query. |
ResourceTypeBadge |
type slug → per-type color chip (rules amber, apicalls green, llm pink, …). |
ActionBadge |
Diff actions: CREATE · UPDATE · SKIP · CONFLICT. |
InfiniteScrollSentinel |
Intersection-observer load-more trigger. |
CommandPalette |
Global Ctrl+K. Opens via its store, not props. |
CreateOrWizardDialog |
"Quick create or launch the wizard" fork. |
ModeSwitcher, RefetchErrorNotice |
Mode switch; background-refetch failure notice. |
UpdateCheckCard |
"Is a newer EDDI released?" panel for the dashboard. No props. Opt-in — issues no request until the operator asks. |
ChipInput |
A list of short values entered one at a time (scopes, origins, keywords). values/onChange, plus pending/onPendingChange — the half-typed text is the caller's state — and optional validate. |
StepDots |
Wizard progress (total, current); announces the step to screen readers. |
ConnectionReferenceButton, ConnectionReferenceWarning |
Insert a ${connection:…} reference, and explain in place why a value will be refused. Only where the backend resolves references (httpcall headers, MCP / A2A apiKey). |
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.
- 16d ago Changed · +8 lines · +1 tokens per session b847de99144d
- 29d ago First seen · 134 lines · 39 tokens per session scan A 251e18f3a6bb
eddi-ui is a skill published in the GitHub repository labsai/EDDI (384 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 2,512 once invoked, about $0.0002 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 2026-09-17.
Other skills, from other repositories
shadcn-ui
Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like…
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
tamagui-v6-config
Tamagui v6 theme system: the light/dark/accent/brand/inverse/level/active theme family, the background-active one-off key, and recipe-tree authoring with createV6Config. Use when choosing a theme for a surface, building a selected/emphasis state, or authoring a custom v6 colors pack.
tamagui-theme-generator
Generate custom Tamagui themes, color palettes, and preview URLs. Use when creating or refining a color scheme, authoring light/dark palettes with brand accents, or previewing generated themes in the browser.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.