A test procedure for running a DevDb VS Code extension in a separate temporary VS Code window and controlling it with Playwright, a browser-style automation tool.

It is for opening the extension panel, clicking and typing in its webview, running commands, reading messages and editor tabs, taking screenshots, and inspecting logs.

It lets developers test the extension without changing their normal VS Code setup, stored credentials, or open session.

How damms005/devdb-vscode configures Claude Code

About the project

DevDb is a VS Code extension that detects a project's database and displays its tables and data in an editor panel. Developers use it to inspect, filter, edit, query, and export database contents while working in VS Code, Cursor, or Windsurf.

damms005/devdb-vscode · 1,451 stars · on GitHub · marketplace.visualstudio.com

Reuse

Borrowing it

Nothing to install: this file belongs to damms005/devdb-vscode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/damms005/devdb-vscode/main/.claude/skills/run-devdb/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/damms005/devdb-vscode

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/damms005/devdb-vscode/run-devdb/github.svg)](https://agentmods.dev/skills/damms005/devdb-vscode/run-devdb)

Your own site

<a href="https://agentmods.dev/skills/damms005/devdb-vscode/run-devdb"><img src="https://agentmods.dev/badge/skills/damms005/devdb-vscode/run-devdb/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/damms005/devdb-vscode/run-devdb"><img src="https://agentmods.dev/badge/skills/damms005/devdb-vscode/run-devdb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,002 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00129	$0.08002
Opus 5.5	$0.00052	$0.03201
Sonnet 5.5	$0.00026	$0.01600
Haiku 4.5	$0.00013	$0.00800

Measured 26d ago against content hash 74d6de0f937a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

run-devdb 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 26d ago.

The scan reads SKILL.md. This mod also ships 16 executable files (bridge/extension.js, driver.mjs, local-datastores/certs/gen-certs.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/run-devdb/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run and drive DevDb

driver.mjs downloads a VS Code build (cached in .vscode-test/), starts it through Playwright's _electron with this repo as the extension under development, and runs commands against the VS Code window and the DevDb webviews. It never touches the user's real VS Code: it uses its own --user-data-dir and --extensions-dir under $DEVDB_DRIVER_DIR, --disable-extensions (only DevDb and the driver bridge load), and --use-inmemory-secretstorage (no keychain access, no stored licenses). It runs next to an open VS Code.

The window does not take focus: on macOS the driver hides the app (as after Cmd+H) and shows the window inactive, with background throttling off, so it still renders for screenshots and input. The Dock icon can bounce for a moment at start. Cmd+Tab to it to watch it live. On Windows and Linux the window is minimized. Input goes to the window through Playwright, not through the OS keyboard.

The driver also loads bridge/ (a test-only extension): a small HTTP server on 127.0.0.1 that runs VS Code commands with arguments (exec) and code in the extension host (host-eval). The port goes to $DEVDB_DRIVER_DIR/bridge.port.

All paths are relative to the repo root.

Setup (once)

ln -s <main-checkout>/node_modules node_modules   # only in a git worktree without node_modules
npm install --prefix .claude/skills/run-devdb

The first run downloads VS Code stable (about 300 MB) into .vscode-test/. Later runs reuse it.

Build

The driver runs dist/extension.js, so build after each code change. For driver runs, point the license API at the driver's local mock (see License):

DEVDB_LICENSE_API_BASE=http://127.0.0.1:47181/api/license node esbuild.js

node esbuild.js bundles the extension only (about 1 s). npm run compile also runs tsc --noEmit.
The webview UI is ui-shell/dist/assets/* (committed). Rebuild it (cd ui-shell && npm run build, needs ../../devdb-ui) only when you test a change in the devdb-ui repo.

Read the full file on GitHub · 324 lines

Files

What ships with it

34 files 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.

Changes

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.

26d ago Changed · +13 lines 74d6de0f937a
27d ago First seen · 311 lines · 129 tokens per session scan A 4b2e0545c391

Subscribe to this mod's changes

run-devdb is a skill published in the GitHub repository damms005/devdb-vscode (1,451 stars, last pushed 8d ago), licensed MIT. It adds 129 tokens to every session and 8,002 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-02.

Browser automation E2E testing Testing

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

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".

get-bb/bb · 57 tokens

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.

anthropics/skills · 35 tokens

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.

hashgraph-online/awesome-codex-plugins · 58 tokens

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…

PostHog/posthog-foss · 112 tokens

devdb-vscode: Skill for Claude Code