va-preview

va-preview is a skill for Claude Code, Codex from jazzenchen/VibeAround. It costs 58 tokens per session (794 once invoked), scanned A, original, MIT.

A tool that starts a shareable live preview of a web page or web application. It shows files served by a development server in a browser on a computer or phone.

In plain words
What is it for?
Use it after starting a development server or creating HTML, CSS, or JavaScript files. It can also be used when you ask to see a web artifact, and requires the VibeAround service.
Why use it?
You may need to see a web change running before you can review it properly. A live preview makes the result available through a browser link.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after starting a development server or creating HTML, CSS, or JavaScript files. It can also be used when you ask to see a web artifact, and requires the VibeAround service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jazzenchen/vibearound/va-preview
Install

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.

Any agent
npx skills add jazzenchen/VibeAround --skill va-preview
Clone the repo
git clone --depth 1 https://github.com/jazzenchen/VibeAround

Made for: Claude Code, Codex.

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.

agentmods badge for va-preview

README.md
[![agentmods](https://agentmods.dev/badge/skills/jazzenchen/vibearound/va-preview.svg)](https://agentmods.dev/skills/jazzenchen/vibearound/va-preview)
Your own site
<a href="https://agentmods.dev/skills/jazzenchen/vibearound/va-preview"><img src="https://agentmods.dev/badge/skills/jazzenchen/vibearound/va-preview.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00794
Opus 5 $0.00029 $0.00397
Sonnet 5 $0.00012 $0.00159
Haiku 4.5 $0.00006 $0.00079

Measured 4d ago against content hash f9089b67568c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

va-preview 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 4d 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.

src/skills/claude/va-preview/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeAround Preview

Preview exactly one local source through VibeAround: a running web server or a Markdown file.

Workflow

1. Prepare one source

  • Server: Reuse the intended server when it is still running. Otherwise start it with the framework's automatic port selection and wait until it is reachable at 127.0.0.1:<port>. VibeAround registers that port in memory; closing that Preview or the daemon kills the process currently listening there.
  • Markdown: Verify that the requested file exists. No separate static-file server is needed.

VibeAround never restores a Preview after restart; call va_mcp_preview again when needed. Registered Server ports are cleaned at shutdown and again at the next startup if shutdown was interrupted.

2. Add optional conversation identity

Pass $VIBEAROUND_THREAD_ID when present. If an exact current session ID is readily available, pass it with agent_kind: "claude". Both are optional; do not delay or block Preview when either is unavailable. These fields only let Preview chat inherit the current task as context. They never control Preview or server lifetime.

3. Call va_mcp_preview

Pass exactly one of port or file, plus cwd.

For a server:

Tool: va_mcp_preview
Server: vibearound
Arguments:
  port: <local server port>
  cwd: "<current working directory>"
  thread_id: "<value of $VIBEAROUND_THREAD_ID if present>"
  agent_kind: "claude"  (pass with session_id)
  session_id: "<exact current session ID if available>"
  title: "<short title>"  (optional)

For Markdown:

Tool: va_mcp_preview
Server: vibearound
Arguments:
  file: "<absolute path, or path relative to cwd>"
  cwd: "<current working directory>"
  thread_id: "<value of $VIBEAROUND_THREAD_ID if present>"
  agent_kind: "claude"  (pass with session_id)
  session_id: "<exact current session ID if available>"
  title: "<document title>"  (optional)

If the workspace is not registered, call va_mcp_register_workspace with cwd, then retry.

Read the full file on GitHub · 77 lines

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.

  1. 4d ago Changed · +2 lines · +15 tokens per session f9089b67568c
  2. 8d ago First seen · 75 lines · 43 tokens per session scan A cb25f9dc11c4

Subscribe to this mod's changes

va-preview is a skill published in the GitHub repository jazzenchen/VibeAround (523 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 794 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.