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 agentmods add skills/vvedantb/eva/no-ui-flashnpx skills add vvedantb/eva --skill no-ui-flashgit clone --depth 1 https://github.com/vvedantb/evaWrote 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/vvedantb/eva/no-ui-flash)<a href="https://agentmods.dev/skills/vvedantb/eva/no-ui-flash"><img src="https://agentmods.dev/badge/skills/vvedantb/eva/no-ui-flash.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.01669 |
| Opus 5 | $0.00046 | $0.00834 |
| Sonnet 5 | $0.00018 | $0.00334 |
| Haiku 4.5 | $0.00009 | $0.00167 |
Grade A, and why
no-ui-flash 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Never flash the wrong UI
Client-rendered apps have a window between first paint and the moment client-side data resolves. The classic bug is filling that window with a placeholder that bets on one outcome — and losing the bet:
- An app-shell skeleton (sidebar, nav, content cards) shown to a signed-out visitor who is about to be bounced to login. They're shown an app they'll never reach, then a jarring swap.
- A results-grid skeleton on a search/list page that resolves to "no results found" — the skeleton promised content that doesn't exist.
- A light-theme first paint that snaps to dark once a preference loads.
- A skeleton for a route that turns out to be a 404.
The rule: render the placeholder for the state you have verified, not the state you hope for. When you can't verify, render a placeholder that's correct in every outcome (neutral, layout-stable) — not the happy path's. Getting there is three layers; each makes the next one's job smaller.
Layer 1 — resolve the state at the edge, before the document is served
The server/edge that serves the SPA's HTML usually already holds what the client will spend a round trip discovering. Use it there:
- Auth: most session schemes verify with no upstream round trip — sealed/signed cookies verify with local crypto, JWTs against a cached JWKS. Gate document requests: signed out →
302 /login?returnTo=<path>before any app HTML exists. The wrong shell can't flash if it's never served. Anyone who receives the SPA at a gated path is now known to be signed in — which makes the client's skeleton honest again. - Data-shaped states: if the edge can cheaply answer "empty vs. populated" (a count, a KV flag, a cookie recording last-known state), it can serve the right variant — empty-state HTML, the populated shell, a redirect to onboarding — instead of a one-skeleton-fits-all document.
- Preferences (theme, locale, density): read the preference cookie at the edge and serve the correct variant in the initial HTML. A class on
<html>beats a client-side flip.
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 · 65 lines · 92 tokens per session scan A e437ed5e30bf
no-ui-flash is a skill published in the GitHub repository vvedantb/eva (101 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,669 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 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
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.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…