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 veithly/vibeshell --skill gatewaygit clone --depth 1 https://github.com/veithly/vibeshellWrote 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/veithly/vibeshell/gateway)<a href="https://agentmods.dev/skills/veithly/vibeshell/gateway"><img src="https://agentmods.dev/badge/skills/veithly/vibeshell/gateway/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/veithly/vibeshell/gateway"><img src="https://agentmods.dev/badge/skills/veithly/vibeshell/gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00378 |
| Opus 5 | $0.00017 | $0.00189 |
| Sonnet 5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
vibeshell 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 today.
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.
What it actually says
VibeShell Gateway
Use the bundled gateway.mjs next to this file. It discovers the local
Gateway, starts the visible VibeShell app when needed, authenticates without
exposing the token, and handles MCP setup automatically.
node gateway.mjs list
node gateway.mjs connect <server-name-or-id>
node gateway.mjs send <session-ref> "uname -a"
node gateway.mjs read <session-ref>
node gateway.mjs call <tool> '{"...":"..."}'
The output uses short, unambiguous server/session references. Full UUIDs remain
accepted when a tool is called directly. Do not invoke vshell, start a
headless daemon, open a second session master, or request raw SSH credentials.
For commands the user should see, always use send (MCP session_send_input)
so the command, output, shell state, and working directory stay in the visible
terminal. Use exec only when the user explicitly asks for isolated/background
execution. Risky commands fail closed until the user approves them in the
VibeShell dialog; credentials remain in the GUI.
Use call for SFTP and other tools. Prefer rg before broad downloads,
get_content/sftp_read for text, edit_file for exact replacements, and
explicit destructive options only when the user requests them.
Common tools: server_list, session_create, session_send_input,
session_read, exec, sftp_upload_directory, sftp_sync_directory,
get_content, edit_file, add_file.
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.
- today First seen · 37 lines · 34 tokens per session scan A 1f1c7f1ce5a2
vibeshell is a skill published in the GitHub repository veithly/vibeshell (79 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 378 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
json-ui
CRITICAL: Use for json-ui component rendering and development. Triggers on: json-ui, json render, component catalog, report render, HTML report, I18nString, i18n, bilingual, language switch, dual language, PaperHeader, AuthorList, Abstract, MetricsGrid, Section, Highlight, Zod schema, catalog.ts, cli.ts…
panel-app-react-vite-creator
Create or update an engineering-style NextClaw Panel component with pnpm, Vite, React, TypeScript, and Tailwind CSS, then build it into a static .panel directory inside a schema v2 package or an explicitly loose workspace Panel. Use for modern, reusable, complex, Agent-powered, typed Panel interfaces.
netcatty-tool-cli
Use this skill when an external agent needs to operate on Netcatty sessions through Skills + CLI instead of the netcatty-remote-hosts MCP server.
internet_search
Instructions for using a local search script to retrieve current web results as JSON, including titles, links, summaries, and sources.
react-router-v7-app
Implements React Router v7 app structure, routing patterns, and component templates. Use when creating or modifying React Router v7 applications to ensure consistent folder structure, data loading patterns, and component architecture.