New to Claude Skills? Learn how to install them →

vercel-labs on GitHub

d3k Agent Runtime

OfficialFree

Streamline web project testing and debugging with d3k.

by vercel-labs1.6k stars on vercel-labs/dev3000
1 views
Updated Jul 31, 2026
Get this skill

Free · Opens the source repo

What d3k Agent Runtime does

d3k is a specialized local web runtime designed for developers who need to efficiently test, debug, and develop web projects. It manages a stable development environment by starting a dev server behind a Portless URL and using a project-stable Chrome profile. This setup allows for comprehensive monitoring of server logs, browser console output, network activity, and user interactions, all captured in a unified timeline. The skill is particularly useful for developers who need to reproduce browser issues or conduct thorough testing without the overhead of managing multiple environments.

When a user engages with d3k, the skill automates the preparation of the runtime, ensuring that the development server and browser are ready for use. It can operate in two modes: user-driven testing, where the user reproduces an issue while d3k monitors the session, and agent-driven testing, where d3k autonomously interacts with the browser to identify problems. This flexibility allows developers to choose their preferred workflow while ensuring that all necessary evidence is collected for analysis.

The skill also emphasizes safety and stability by maintaining a dedicated Chrome profile for each project, preserving login states and cookies. This is crucial for applications that require secure authentication flows, as it prevents issues that can arise from using different browser instances. With its straightforward command-line interface, d3k simplifies the process of starting, monitoring, and debugging web applications, making it an essential tool for developers looking to enhance their productivity and streamline their development process.

When to use it

Use d3k when you need a reliable environment for testing web projects, especially when dealing with browser-specific issues or when you want to capture detailed logs and interactions during development.

When not to use it

This skill is not suitable for projects that do not require a browser-based testing environment or for scenarios where lightweight or headless testing is preferred without the need for detailed logging.

What you can build with it

Testing a Web Application

When a developer needs to test a web application, they can use d3k to start the runtime and monitor the browser while reproducing issues.

Debugging Browser-Specific Issues

If a user encounters a bug that only appears in certain browsers, d3k allows them to capture detailed logs and interactions to diagnose the problem.

Capturing Logs for Analysis

Developers can utilize d3k to run their project and automatically collect logs, making it easier to review performance and errors.

How to install d3k Agent Runtime

View source

1. Install with the skills CLI

npx skills add vercel-labs/dev3000/d3k --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by vercel-labs

d3k Agent Runtime

d3k is the local web runtime for this task. It starts the dev server behind a stable Portless URL, owns a project-stable Chrome profile, and records server logs, browser console output, network activity, interactions, and screenshots in one timeline.

When this skill triggers, operate d3k. Do not merely tell the user how to run it.

Interpret the Request

  • "Let me test/dev my project with d3k": prepare the runtime and headed browser, confirm it is ready, then hand control to the user. Wait for them to reproduce the issue before inspecting evidence.
  • "Test/debug/fix this with d3k": prepare the runtime, then drive the managed browser and investigate autonomously.
  • If ambiguous, start the runtime and browser first. That action is safe and useful for either path.

Start or Reuse d3k

Run from the project root.

  1. Check for an existing project runtime:
d3k status --json

If it reports "running": true, reuse it. Do not start a second dev server or browser.

  1. If d3k is not installed, install it:
bun install -g dev3000

Use npm install -g dev3000 only when Bun is unavailable.

  1. Start d3k with the agent's shell/process tool as a retained background or yielded session:
d3k --no-agent --no-tui -t

Do not wait for this long-running command to exit. Keep its process/session handle so you can monitor or stop it later. Prefer the execution tool's background/session support over shelling with &.

If the target URL is already known, pass it so the managed browser opens there:

d3k --no-agent --no-tui -t --app-url "<url>"

Let d3k auto-detect the package manager, dev command, and port. Add --command, --script, or --port only when detection is wrong or the user specified them.

  1. Poll until the runtime is ready:
d3k status --json

A successful status response is the readiness boundary. Prefer the reported Portless appUrl; the underlying app port may change between runs. If startup fails, inspect the retained process output and d3k logs --type server; do not launch a separate dev server.

User-Driven Testing

When the user says "let me test":

  1. Confirm the status response includes the app URL and "browserConnected": true.
  2. Tell the user the monitored browser is ready.
  3. Keep the d3k process running and wait for the user to reproduce the behavior.
  4. When they report that it happened, begin with:
d3k errors --context
d3k logs -n 200

Do not replace the headed browser with automation while the user is testing.

Agent-Driven Testing

Drive the exact browser d3k is monitoring:

d3k agent-browser snapshot -i
d3k agent-browser click @e2
d3k agent-browser fill @e3 "text"
d3k errors --context

Use --require-d3k-browser when opening a URL so failure cannot silently create another browser:

d3k agent-browser --require-d3k-browser open "<url>"

After every reproduction or code change, replay the relevant interaction and check d3k errors --context again.

Evidence Commands

Prefer these over ad-hoc log scraping:

d3k status --json
d3k errors --context
d3k logs -n 200
d3k logs --type browser
d3k logs --type server

Artifacts live under ~/.d3k/<project>/, including session.json, logs, screenshots, and the Chrome profile.

Browser and Auth Safety

d3k must own browser startup by default. Its per-project Chrome profile preserves login state, cookies, and local storage.

For Google OAuth, Supabase auth, and other auth-sensitive flows, never substitute raw Chrome, Playwright, a browser MCP session, manual CDP attachment, or agent-browser --profile. Those paths use a different browser/profile and can trigger "This browser or app may not be secure."

If the managed browser is unavailable, stop or interrupt the retained d3k process and restart d3k cleanly. Do not work around it by creating another browser.

Use --headless only for CI or when explicitly requested. Use --servers-only only when browser monitoring is intentionally unwanted.

Operating Rules

  • Do not run npm run dev, bun run dev, or another dev server alongside d3k.
  • Do not start a second d3k when d3k status --json reports an active one.
  • Keep d3k alive across edits and retests.
  • Preserve the project-stable Chrome profile unless the user explicitly asks for a fresh profile.
  • Leave the runtime running when handing a headed browser to the user; stop it only when asked or when the task requires a clean restart.
  • Portless routing is the default. Use --no-portless or PORTLESS=0 only when direct localhost routing is explicitly required.

Frequently asked questions about d3k Agent Runtime

Similar skills