vercel-labs/dev3000 is a local web debugging runtime that records a web app's server logs, browser events, errors, network activity, interactions, and screenshots in one timestamped timeline. Coding agents use it to run and inspect web applications while reproducing bugs. Its catalogue add-ons teach agents how to operate the runtime and examine its debugging evidence.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vercel-labs/dev3000 --skill d3kgit clone --depth 1 https://github.com/vercel-labs/dev3000Wrote 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/vercel-labs/dev3000/d3k)<a href="https://agentmods.dev/skills/vercel-labs/dev3000/d3k"><img src="https://agentmods.dev/badge/skills/vercel-labs/dev3000/d3k/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/vercel-labs/dev3000/d3k"><img src="https://agentmods.dev/badge/skills/vercel-labs/dev3000/d3k.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 103 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.
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 | $0.00068 | $0.01403 |
| Opus 5.5 | $0.00027 | $0.00561 |
| Sonnet 5.5 | $0.00014 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
d3k 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- d3k — 92% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
- Check canonical Portless readiness before starting any app process:
d3k portless status --json
If "setupRequired": true, run:
d3k portless setup
On macOS this opens the system administrator authorization dialog. Wait for the user to approve it, then rerun d3k portless status --json. Do not start d3k until "canonical": true, "serviceInstalled": true, and "setupRequired": false. If authorization is declined or unavailable, stop and explain the blocker. Never silently substitute direct localhost.
- Check for an existing project runtime:
d3k status --json
Reuse it only if it reports "running": true, "ready": true, "routing": "portless", "browserConnected": true, and a genuinely port-free https://...localhost appUrl. If an active session reports "routing": "direct", stop that retained d3k session and restart after Portless is ready. Do not start a second dev server or browser.
- If d3k is not installed, install it:
bun install -g dev3000
Use npm install -g dev3000 only when Bun is unavailable.
- Start d3k with the agent's shell/process tool as a retained background or yielded session (non-TUI by default):
What ships with it
2 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.
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.
- 1mo ago First seen · 143 lines · 68 tokens per session scan A 13ac78a7c8eb
d3k is a skill published in the GitHub repository vercel-labs/dev3000 (1,584 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 1,403 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
miniapp-devtools-gui-check
Use host-side WeChat DevTools automation to inspect GUI-only runtime and interaction failures that do not show up in CLI preview. Trigger when page entry, taps, websocket-based DevTools automation, or run-directory evidence such as report.json and trace.log are needed to separate repo bugs from IDE session problems…
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.