Borrowing it
Nothing to install: this file belongs to juliakrivchikova/AccordAgents-desktop-app. 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/juliakrivchikova/AccordAgents-desktop-app/main/.agents/skills/electron-desktop-qa/SKILL.mdgit clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-appWrote 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/juliakrivchikova/accordagents-desktop-app/electron-desktop-qa)<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/electron-desktop-qa"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/electron-desktop-qa/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/juliakrivchikova/accordagents-desktop-app/electron-desktop-qa"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/electron-desktop-qa.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 | $0.00054 | $0.01874 |
| Opus 5 | $0.00027 | $0.00937 |
| Sonnet 5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
electron-desktop-qa 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 7d 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 -s --max-time 2 http://127.0.0.1:9222/json/version How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electron Desktop QA
Use this skill for AccordAgents renderer QA, UI bug reproduction, visual checks, and any task that asks you to see, screenshot, click, type into, scroll, or read DOM/CSS state in the desktop app.
Rules
- The Electron renderer via CDP is the source of truth.
- Do not use plain
http://127.0.0.1:5173/as desktop validation. It lacks the Electron preload and can crash or differ from the real app. - Do not use macOS screenshots, AppleScript, window-focus tricks, or a generic browser as a substitute.
- Do not report desktop UI QA as blocked until the escalated CDP path below has been attempted and failed.
Workflow
-
Read
docs/inspecting-the-desktop-app.mdif you need details beyond this checklist. -
Check whether a debuggable app is already available:
curl -s --max-time 2 http://127.0.0.1:9222/json/version -
If localhost access fails with
Operation not permitted, or Vite fails withlisten EPERM, rerun the same important command with the provider's escalation or approval mechanism. For Codex, usesandbox_permissions: "require_escalated"with a concrete justification. -
Prefer a separate production Electron launch before using Vite:
npm run build node_modules/.bin/electron . --remote-debugging-port=9222Keep the Electron command running while you test. If port 9222 is occupied, use another port such as 9223 and pass that port to
attach({ port: 9223 }). When the user asks for an instance that must survive the turn, use the detachedlaunchctlrecipe below instead ofnohup. -
Verify attachment and capture proof:
curl -s --max-time 2 http://127.0.0.1:9222/json/version node scripts/screenshot.cjs qa-initial.png -
Inspect the live renderer with
scripts/cdp.cjs, not source guesses:const { attach } = require("./scripts/cdp.cjs"); (async () => { const app = await attach(); const state = await app.evaluate(`(() => ({ title: document.title, text: document.body.innerText.slice(0, 4000), buttons: [...document.querySelectorAll("button")].map((b, i) => ({ i, text: b.innerText, aria: b.getAttribute("aria-label"), title: b.getAttribute("title"), disabled: b.disabled, cls: b.className })).slice(0, 100) }))()`); console.log(JSON.stringify(state.result.value, null, 2)); app.close(); })();
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.
- 7d ago Changed · +98 lines d79a3429d994
- 11d ago First seen · 99 lines · 54 tokens per session scan A 93df1fdffa8b
electron-desktop-qa is a skill published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,874 once invoked, about $0.0003 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
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…