Borrowing it
Nothing to install: this file belongs to novasamatech/nova-spektr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/novasamatech/nova-spektr/dev/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/novasamatech/nova-spektrWrote 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/novasamatech/nova-spektr/verify)<a href="https://agentmods.dev/skills/novasamatech/nova-spektr/verify"><img src="https://agentmods.dev/badge/skills/novasamatech/nova-spektr/verify/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/novasamatech/nova-spektr/verify"><img src="https://agentmods.dev/badge/skills/novasamatech/nova-spektr/verify.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 | $0.00027 | $0.00665 |
| Opus 5 | $0.00014 | $0.00332 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
verify 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 8d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying renderer changes in a real browser
Launch
pnpm start:rendererserves the renderer at https://localhost:3000 (Vite, ~30s until first page finishes bundling). The full Electronpnpm startis NOT needed for renderer-only changes — the app works in a plain browser.- The mkcert-style dev cert covers
localhostonly —https://127.0.0.1:3000throws a cert interstitial. To get an isolated storage origin (fresh IndexedDB/localStorage without touching existing dev data), start a second instance:pnpm start:renderer --port 3001— same cert hostname, different origin. - Dev data (wallets, operations) lives per-origin.
localhost:3000and:3001may already contain the developer's real dev profiles — treat them as user data: read-only driving is fine, don't import DBs or clear storage, and revert any localStorage flag you flip.
Getting a wallet
- Onboarding page (dev builds) has an Import database button accepting a Dexie export JSON; seeds live in
tests/system/data/db/(e.g.transfers/transfers_tests_db.json). Only do this on a fresh origin.
Driving gotchas
- Browser-extension
typeactions drop characters in the recipient Combobox — SS58 addresses arrive mangled and fail checksum validation. Set values via the native setter instead:Object.getOwnPropertyDescriptor(HTMLInputElement.prototype,'value').set.call(input, addr); input.dispatchEvent(new Event('input',{bubbles:true})) - A valid stranger address for Polkadot-family chains:
13mAjFVjFDpfa42k2dLdSnUyrSzK8vAySsoudnxX2EKVtfaq(from the system-test fixtures). Don't type addresses from memory — checksum fails read as "Address has incorrect format". - Hash-only
navigatecalls do NOT reload the page — persisted stores (effector-storagepersist) only re-hydrate on a reallocation.reload(). Same-tablocalStorage.setItemdoes not fire storage events either. - Live model state is inspectable via Vite module URLs:
await import('/@fs/<abs-repo-path>/src/renderer/aggregates/<x>/model.ts')then.getState()on stores.knownCount-style sanity values tell you whether you got the app's instance. - Address-book connection state is driven by localStorage key
address-book-has-ever-connected('true'/absent) — flipping it + reload moves the app between never-connected and disconnected (unverifiable) modes without a backend. Fully-connected mode needs real backend auth; cover it with integration tests instead. - The operations table needs a wide window; row action buttons (Approve/Reject) may sit off-viewport — use the extension's
findfor them rather than scrolling blindly.
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.
- 8d ago First seen · 28 lines · 27 tokens per session scan A ed8eea9cf394
verify is a skill published in the GitHub repository novasamatech/nova-spektr (56 stars, last pushed 5d ago), licensed Apache-2.0. It adds 27 tokens to every session and 665 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…