A guide to using the vBot command-line tool to inspect and change the settings and stored state of vBot and its agents.

Reading or changing projects, channels, skills, agent settings, and other vBot configuration.

It helps the agent choose valid commands, check help output, and verify the resulting state instead of assuming a change succeeded.

vbot-docs — Skill for Claude Code and Codex by Vironnimo/vbot

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 Vironnimo/vbot --skill vbot-docs

Clone the repo

git clone --depth 1 https://github.com/Vironnimo/vbot

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vironnimo/vbot/vbot-docs/github.svg)](https://agentmods.dev/skills/vironnimo/vbot/vbot-docs)

Your own site

<a href="https://agentmods.dev/skills/vironnimo/vbot/vbot-docs"><img src="https://agentmods.dev/badge/skills/vironnimo/vbot/vbot-docs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vironnimo/vbot/vbot-docs"><img src="https://agentmods.dev/badge/skills/vironnimo/vbot/vbot-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,945 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.01945
Opus 5.5	$0.00012	$0.00778
Sonnet 5.5	$0.00006	$0.00389
Haiku 4.5	$0.00003	$0.00194

Measured today against content hash a3bbe762a43f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vbot-docs 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.

The scan reads SKILL.md. This mod also ships 3 executable files (assets/extensions/guard_bash.py, assets/extensions/word_count.py, assets/extensions/workflow_command/extension.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

resources/skills/vbot-docs/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vBot

Use vbot through the shell Tool to inspect and configure the application. The server runs Agents and owns the state used by the CLI, TUI, WebUI, Desktop, and Channels. A saved configuration change affects that server instance.

Choose the area and action first: vbot <area> <action> [target] [options]. Related actions can be grouped, for example vbot project override set, vbot channel token set, and vbot skill file write. There is no fixed word count. Resource ids are positional; flags supply options and values. Use the commands shown by help instead of inventing action flags such as --restart.

Start with vbot help or vbot <area>, then narrow to vbot <area> <group> --help. Bare command groups show help without executing an action. Collection plurals also work; prefer the names and action paths shown in help. Older compound command spellings remain compatible. Syntax errors may suggest a correction but never execute it automatically.

[OK] confirms command completion; [WARN] calls out pending work or a reported limitation; [ERROR] marks failure. Read the returned state before claiming runtime readiness. Progress and completion notices for management commands go to stderr; stdout retains the data, including complete JSON and content reads. --output plain suppresses these extra notices and uses the stable data layout. Terminal output is readable by default; --output human requests that layout in a capture too. Lifecycle and Doctor commands retain their dedicated reports.

Start with the task

For a focused question about a past conversation, use session_search and answer from sufficient evidence. Read references/session-search.md when you need more evidence, complete wording, a Session list, or a Tool Result.

Read the relevant reference below before writing. It explains scope, replacement rules, and verification. Use vbot <area> <command> --help for exact arguments; primary ids are positional.
Inspect the affected resource. Reuse exact ids from results. Read the complete content before replacing a Skill, prompt block, or automation prompt; a list preview is insufficient.
Apply the requested change, preserving unrelated fields. Omitted update flags normally leave fields unchanged; list and policy flags replace their entire value. Read the area's exceptions.
Check the result for saved values, warnings, pending work, and failures. A saved Agent without an effective Model cannot run; an enabled Channel may still fail to connect; a scheduled restart has not completed. Verify the user's intended behavior and report what the evidence establishes.

Read the full file on GitHub · 73 lines

Files

What ships with it

25 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.

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.

today Changed a3bbe762a43f
9d ago First seen · 73 lines · 31 tokens per session scan A 00a99e73532f

Subscribe to this mod's changes

vbot-docs is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 1,945 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.

Building agents LLM Productivity Python agent-skills ai-agents anthropic self-hosted

content-hash-cache-pattern

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

affaan-m/ECC · 30 tokens

kalender

Calendar skill with user-adaptive backend selection (Flag 3). Default: local SQLite store. Optional: Google Calendar MCP, Routinika or UpToday as backend — controlled via assist/prefs.json. Without preference the LLM asks the user interactively.

ellmos-ai/skills · 55 tokens

bewerbungsexperte

Spezialist fuer den gesamten Bewerbungsprozess. Analysiert Stellenanzeigen, optimiert Profile (LinkedIn/CV) und generiert massgeschneiderte Anschreiben. Generiert ASCII-Lebenslaeufe aus einer SQLite-Datenbank und Ordnerstruktur. cvgenerator.py ist standalone portiert -- keine BACH-Runtime noetig.

ellmos-ai/skills · 78 tokens

vbot-docs