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 gusbavia/fabric-apps-skills --skill fabric-app-lakehouse-livegit clone --depth 1 https://github.com/gusbavia/fabric-apps-skillsWrote 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/gusbavia/fabric-apps-skills/fabric-app-lakehouse-live)<a href="https://agentmods.dev/skills/gusbavia/fabric-apps-skills/fabric-app-lakehouse-live"><img src="https://agentmods.dev/badge/skills/gusbavia/fabric-apps-skills/fabric-app-lakehouse-live/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/gusbavia/fabric-apps-skills/fabric-app-lakehouse-live"><img src="https://agentmods.dev/badge/skills/gusbavia/fabric-apps-skills/fabric-app-lakehouse-live.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 | $0.00150 | $0.01501 |
| Opus 5 | $0.00075 | $0.00750 |
| Sonnet 5 | $0.00030 | $0.00300 |
| Haiku 4.5 | $0.00015 | $0.00150 |
Grade A, and why
fabric-app-lakehouse-live scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X OPTIONS <graphql-endpoint> -H "Origin: https://<your-app-url>" \ How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabric App · Lakehouse Live Bridge
The browser acquires a delegated Fabric token (the signed-in user's own identity) and POSTs straight to a Lakehouse "API for GraphQL" endpoint. Live data, per-user permissions and RLS, zero infrastructure, no secrets in the bundle.
browser → MSAL (Entra SSO, delegated) → POST → GraphQL API over the Lakehouse
A working reference implementation exists in the fabric-apps-starter repo, template-lakehouse-live/ (Vite + React + MSAL, query console + token inspector).
The recipe — order matters, each step gates the next
1. Validate CORS before writing code. Preflight the GraphQL endpoint with the app origin:
curl -X OPTIONS <graphql-endpoint> -H "Origin: https://<your-app-url>" \
-H "Access-Control-Request-Method: POST" -i
# want: 200 + Access-Control-Allow-Origin echoing your origin
Fabric allows Fabric Apps origins by default. If this fails, nothing downstream can work.
2. MSAL singleton, initialized BEFORE render. When the browser returns from login.microsoftonline.com, the SPA boots again and MSAL must parse the auth response on that load:
// lib/msal.ts
export const msal = new PublicClientApplication({
auth: { clientId, authority: `https://login.microsoftonline.com/${tenantId}`,
redirectUri: window.location.origin },
cache: { cacheLocation: "sessionStorage" },
});
export async function bootstrapMsal() {
await msal.initialize();
await msal.handleRedirectPromise(); // skip this → sign-in silently never lands
}
// main.tsx: bootstrapMsal() runs before createRoot(...).render(...)
Prefer loginRedirect over popups for SPAs: no blocked windows, no blank popup pages, works embedded and standalone.
3. App registration (Entra portal):
- Authentication → add platform → Single-page application → redirect URI = the app URL (plus
http://localhost:5173for dev). Authorization Code + PKCE; leave both implicit-grant checkboxes UNchecked. - API permissions → Power BI Service → Delegated →
GraphQLApi.Execute.All→ grant admin consent. This is THE permission that gates query execution;Tenant/Workspace/Dataset/Item.Read.Allall return 403 without it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 116 lines · 150 tokens per session scan A 96b87039d877
fabric-app-lakehouse-live is a skill published in the GitHub repository gusbavia/fabric-apps-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 1,501 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
claude-api-in-prototypes
Call Claude from your HTML artifacts via window.claude.complete.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
core
Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.
playwright
Playwright E2E testing patterns. Trigger: When writing Playwright E2E tests (Page Object Model, selectors, MCP exploration workflow). For Prowler-specific UI conventions under ui/tests, also use prowler-test-ui.
thinking-orbs
Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface needs a semantic working, searching, solving, listening, composing, or shaping state; when replacing a generic spinner with an AI activity…
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.