# Vbot Cli

> Configure and operate vBot through the vbot CLI. Use when asked to start, stop, restart, or update the server, set up provider credentials (API key or OAuth), or list/add/edit/remove agents, projects, sessions, channels (Telegram, Discord), cron jobs, task-model bindings, prompts, extensions, or settings — or to inspect models, skills, tools, logs, debug traces, and usage statistics (tokens, runs…

- **Type:** Skill
- **Install:** `agentstack add skill-vironnimo-vbot-vbot-cli`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Vironnimo](https://agentstack.voostack.com/s/vironnimo)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [Vironnimo](https://github.com/Vironnimo)
- **Source:** https://github.com/Vironnimo/vbot/tree/main/resources/skills/vbot-cli

## Install

```sh
agentstack add skill-vironnimo-vbot-vbot-cli
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# vBot CLI

The `vbot` CLI is the automation surface for configuring and operating a vBot instance: run the command, verify the result, report what changed.

## Rules

- Primary identifiers are positional (`vbot agent show assistant`); secondary parameters are flags. `vbot   --help` shows exact flags plus a usage example.
- Only `server start|stop|restart|status`, `desktop`, `update`, `autostart`, and `doctor` work without a running server. Everything else needs one: check `vbot server status` first, start with `vbot server start` if needed.
- Non-default instance: add `--host`, `--port`, `--data-dir` to every command.
- Prefer CLI commands over direct file edits — settings, agents, channels, cron jobs, prompt blocks, and provider keys all have commands. If a manual JSON edit was unavoidable, validate with `vbot doctor config`.
- Secrets never appear in output or chat. API keys go through `provider set-key`, extension secrets through `extensions  set  --stdin`, channel tokens by env-var name via `--token-env`.
- Inspect before changing; verify after with the matching list/show/status command.
- Follow CLI error hints (`did you mean`, candidate lists) before retrying. If another process occupies the port, report it — don't kill it.
- Finish with a compact report: commands run, what changed, verification result, and any remaining user action (complete an OAuth login, send a Telegram message, ...).

## Conventions

- Model references are `/`, optionally pinned to a connection and credential account with `::[:]` (e.g. `openai/gpt-5.2::api-key:work`).
- Project agents are addressed `agent@projekt` (e.g. `orchestrator@vbot`) in session, cron, and prompt-preview commands; a bare id means an identity agent.
- JSON values (arrays, objects, booleans) are passed as one shell argument: `vbot config set skill_directories '["C:/skills"]'`.
- List-replacing flags (`--allow`, `--allowed-tools`, `--allowed-skills`, `--auto-load`) replace the full list — pass every value that should remain.

## Areas

Read the reference file before using an area's write commands — it has the exact flags and the gotchas.

| Area | Commands | Reference |
|---|---|---|
| `server` | `start` `stop` `restart` `status` | `references/server.md` |
| `update` | update the install from git, restart | `references/server.md` |
| `autostart` | `enable` `disable` `status` | `references/server.md` |
| `desktop` | open the desktop window | `references/server.md` |
| `doctor` | `settings` `config` — validate config files locally | `references/server.md` |
| `provider` | `list` `status` `enable` `disable` `set-key` `unset-key` `connect` `connect-status` `disconnect` | `references/providers.md` |
| `model` | `list` `refresh []` | `references/providers.md` |
| `task-model` | `list` `targets` `options` `set` `clear` | `references/providers.md` |
| `agent` | `list` `show` `create` `update` `delete` | `references/agents-projects.md` |
| `project` | `add` `list` `show` `set` `rm` | `references/agents-projects.md` |
| `session` | `list` `create` `delete` `link-channel` | `references/agents-projects.md` |
| `channel` | `add` `list` `status` `update` `enable` `disable` `remove` | `references/channels.md` |
| `cron` | `list` `create` `update` `delete` `enable` `disable` | `references/cron.md` |
| `config` | show all, `get`, `set` — raw settings keys | `references/configuration.md` |
| `prompt` | `list` `update` `reset` `preview` | `references/configuration.md` |
| `extensions` | `list` `reload` `` ` set` `enable` `disable` | `references/configuration.md` |
| `log` | `list` `read` | `references/diagnostics.md` |
| `debug` | `status` `probe` `traces` `trace` `clear` | `references/diagnostics.md` |
| `statistics` | `overview` `usage` `runs` `errors` `tools` `skills` | `references/diagnostics.md` |
| `skill` | `list` — loadable skills plus invalid-skill diagnostics | — |
| `tool` | `list` — public tools exposed to agents | — |

First-time Telegram bot setup (BotFather, token, chat-id discovery, privacy mode): follow `references/telegram-setup.md`.

## Quick reference

The most common single commands:

```bash
vbot provider set-key   --refresh-models  # activate a provider with a user-supplied key
vbot agent update  --model /      # switch an agent's model
vbot config set                                     # change a settings key (JSON or string)
vbot channel status                                 # channel health + denied inbound chats
vbot server restart                                             # apply .env edits or code changes
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Vironnimo](https://github.com/Vironnimo)
- **Source:** [Vironnimo/vbot](https://github.com/Vironnimo/vbot)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-vironnimo-vbot-vbot-cli
- Seller: https://agentstack.voostack.com/s/vironnimo
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.