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 cognitedata/builder-skills --skill handle-startup-stategit clone --depth 1 https://github.com/cognitedata/builder-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/cognitedata/builder-skills/handle-startup-state)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/handle-startup-state"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/handle-startup-state/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/cognitedata/builder-skills/handle-startup-state"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/handle-startup-state.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 | $0.00094 | $0.02013 |
| Opus 5 | $0.00047 | $0.01007 |
| Sonnet 5 | $0.00019 | $0.00403 |
| Haiku 4.5 | $0.00009 | $0.00201 |
Grade A, and why
handle-startup-state 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle Startup State
Reads the optional initialState string returned by connectToHostApp()
and restores it before first render, so the app opens directly into the
right view instead of always starting from defaults.
Requires @cognite/app-sdk's connectToHostApp() handshake already wired
up. If auth isn't wired up yet, run the
setup-flows-auth skill first.
What initialState actually is
initialState is a single opaque string, present on the object returned
by connectToHostApp():
const { api, initialState } = await connectToHostApp();
Your app never needs to know how it got there — treat it the same way regardless of source:
- A user opened a shareable URL your app previously wrote via
api.syncInternalState(...)(thecustomAppInternalStateURL param). - A host embedded your app with a startup argument baked in (a Flows dashboard widget, or any other surface that programmatically launches your app with initial arguments).
- The app was reloaded and the current URL still has the param from an
earlier
syncInternalStatecall.
All three arrive through the same field. Design your restore logic once and it covers all of them.
Step 1 — Decide your encoding
Pick one encoding and use it consistently:
- Serialized route (a path string) — if your app's state maps cleanly onto a URL you'd otherwise navigate to.
- JSON string — if you need multiple independent fields (active tab, filters, selected IDs). This is the more common choice and the one used below.
Step 2 — Read initialState on mount, defensively
Restore before the first meaningful render. Malformed state must never crash the app — the host cannot guarantee the string is well-formed (it never parses it either), and an older app version may have written a different shape.
import { useEffect, useRef, useState } from 'react';
import { connectToHostApp, type HostAppAPI } from '@cognite/app-sdk';
interface AppState {
activeTab: string;
selectedAssetId?: string;
filters: { status: string };
}
const DEFAULT_STATE: AppState = {
activeTab: 'overview',
filters: { status: 'all' },
};
export function parseInitialState(initialState: string | undefined): AppState {
if (!initialState) return DEFAULT_STATE;
try {
const parsed = JSON.parse(initialState) as Partial<AppState>;
return { ...DEFAULT_STATE, ...parsed };
} catch {
// Malformed or from an incompatible app version — fall back to defaults.
return DEFAULT_STATE;
}
}
export function useAppState() {
const [api, setApi] = useState<HostAppAPI | null>(null);
const [state, setState] = useState<AppState>(DEFAULT_STATE);
const apiRef = useRef<HostAppAPI | null>(null);
useEffect(() => {
connectToHostApp()
.then(({ api: resolvedApi, initialState }) => {
apiRef.current = resolvedApi;
setApi(() => resolvedApi);
setState(parseInitialState(initialState));
})
.catch(() => {
// connectToHostApp rejects when there's no Fusion parent window to
// connect to (e.g. opening the raw Vite dev URL directly instead of
// through Fusion). api and state simply stay at their initial
// values (null / DEFAULT_STATE) — nothing else to do here.
});
}, []);
return { api, state, setState, apiRef };
}
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 · 230 lines · 94 tokens per session scan A ff9d68070eb0
handle-startup-state is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,013 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…