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 jazzenchen/VibeAround --skill va-previewgit clone --depth 1 https://github.com/jazzenchen/VibeAroundWrote 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/jazzenchen/vibearound/va-preview)<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>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00794 |
| Opus 5 | $0.00029 | $0.00397 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
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.
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.
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.
- 4d ago Changed · +2 lines · +15 tokens per session f9089b67568c
- 8d ago First seen · 75 lines · 43 tokens per session scan A cb25f9dc11c4
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.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-rust
This is a Hermes-native rust workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
jikegongyuan-perspective
A writing guide based on GeekPark, a Chinese technology publication and entrepreneur community focused on AI, products, startups, and innovation.