Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jamditis/claude-skills-journalismnpx agentmods add skills/jamditis/claude-skills-journalism/electron-devWrote 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/jamditis/claude-skills-journalism/electron-dev)<a href="https://agentmods.dev/skills/jamditis/claude-skills-journalism/electron-dev"><img src="https://agentmods.dev/badge/skills/jamditis/claude-skills-journalism/electron-dev.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 280 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 281 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 372 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00034 | $0.02853 |
| Opus 5 | $0.00017 | $0.01426 |
| Sonnet 5 | $0.00007 | $0.00571 |
| Haiku 4.5 | $0.00003 | $0.00285 |
Grade A, and why
electron-dev 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electron desktop development
Patterns and practices for building production-quality Electron applications with React and TypeScript.
Security baseline (Electron 30+)
Electron's defaults have hardened over the past several releases. As of Electron 28+, contextIsolation: true and sandbox: true are the defaults for new BrowserWindow instances, most security advice from older guides assumed you had to opt in. You don't anymore; you have to opt OUT, and you should not.
Set explicitly anyway, so a config drift never weakens the security model:
const win = new BrowserWindow({
webPreferences: {
contextIsolation: true, // default since 12, mandatory for any prod app
sandbox: true, // default since 28; renderer runs sandboxed
nodeIntegration: false, // never enable in renderer
webSecurity: true, // never disable
preload: path.join(__dirname, 'preload.cjs')
}
});
Validate every IPC message in main. Don't trust the renderer.
Electron Fuses + ASAR integrity
Electron Fuses are package-time toggles baked into the binary. The two relevant for security distribution:
EnableEmbeddedAsarIntegrityValidation, verifies the app.asar hash at runtime against a hash embedded in the binary. Defends against attackers swapping the asar contents post-install.OnlyLoadAppFromAsar, refuses to load app code from anywhere except the validated asar.
These are opt-in, not default. Enable both for production. Requires @electron/asar 3.1.0+ to generate the asar with embeddable integrity. electron-builder configures this via electronFuses in the build config; @electron/fuses does it programmatically.
CVE-2023-44402 (ASAR integrity bypass via filetype confusion) was the canonical motivation here, without integrity + only-load-from-asar, an attacker who can modify app files can swap behavior silently.
Common renderer-side risks
- Preload script confusion, only expose narrow, typed surfaces via
contextBridge.exposeInMainWorld. Never re-exportipcRendereritself; expose specific methods that map to specific channels. file://IPC and navigation, restrict navigation withwebContents.on('will-navigate', e => e.preventDefault())for windows that shouldn't change URL. DenysetWindowOpenHandlerrequests by default; allow-list specific origins.shell.openExternalwith user input, validate the URL scheme before opening. An attacker-controlledfile://orjavascript:URL hands them code execution.
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.
- 8d ago First seen · 377 lines · 34 tokens per session scan A b61d289f3558
electron-dev is a skill published in the GitHub repository jamditis/claude-skills-journalism (387 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 2,853 once invoked, about $0.0002 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
react-component-generator
Generate React components with TypeScript, proper props, hooks, and accessibility. Use when creating new React components, UI elements, or refactoring existing components.
typescript-dev
Builds full-stack TypeScript apps with Vite 8, React 19, Tailwind CSS v4, shadcn/ui, Biome, Vitest, and Hono. Covers the frontend (Vite/Rolldown build and dev server, type-safe React 19, strict TypeScript 6.0, Tailwind/shadcn styling, Biome lint/format, Vitest) and the Hono 4 backend/edge layer (routing, middleware…
frontend-development
Use this skill for ANY work involving React, Next.js, TypeScript, or Tailwind in the browser layer. This includes building components and pages, but equally covers debugging and fixing frontend issues: CSS/Tailwind classes not applying, form validation behavior, hydration mismatches between server and client renders…
react-architect
React 19 standards — TypeScript strict, feature-based components, hooks-first composition, TanStack Query for server state, zustand for cross-tree client state, Suspense + ErrorBoundary at every async boundary, Radix for a11y. Use when writing or reviewing React components, hooks, or client-side state.
frontend-conventions
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…