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 agentmods add skills/vercel-labs/dev3000/d3knpx skills add vercel-labs/dev3000 --skill d3kgit clone --depth 1 https://github.com/vercel-labs/dev3000What 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 | $0.00068 | $0.01403 |
| Opus 5 | $0.00034 | $0.00701 |
| Sonnet 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 yesterday.
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 — 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.
- yesterday First seen · 143 lines · 68 tokens per session scan A 13ac78a7c8eb
d3k is a skill published in the GitHub repository vercel-labs/dev3000 (1,570 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 1,403 once invoked, about $0.0003 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
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
submit-pr-from-current-changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.
pre-impl-discussion
Conduct a thorough pre-implementation discussion before making significant changes. Use when the user wants to discuss, plan, or evaluate a change before implementing it — especially when they say words like 'discuss', 'evaluate', 'plan', or 'let's talk about'.
inline-vis
Emit a sandboxed inline HTML visualization in an assistant message when a workspace .html file should render in-thread. Use after writing or updating a demo/chart/report HTML file the user should see without opening a panel.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
horse-websocket
Guidelines and workflows for developing and maintaining WebSocket endpoints and protocol upgrades within the Horse framework.