Agent skill

MetaBot CLI

by xvirobotics in xvirobotics/metabot

Documents the unified `metabot` CLI for personal memory, the skill hub, durable agent messaging, the agent registry, T5T status and scheduling.

MITAuto-check passedAgent Workflows

Install MetaBot CLI

skills CLI
$ npx skills add xvirobotics/metabot --skill metabot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xvirobotics/metabot metabot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xvirobotics/metabot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/skills/metabot .claude/skills/metabot && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
metabot
GitHub stars
994
Token cost
~573 tokens
SKILL.md length
215 words
Files
6 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Documents the unified `metabot` CLI for personal memory, the skill hub, durable agent messaging, the agent registry, T5T status and scheduling.

  • Searching or saving notes in MetaBot's shared memory
  • SKILL.md covers Command References, Fast Path, Authentication And Scope and Output
  • Needs METABOT_CORE_TOKEN
  • Sending a durable message to another agent over the Agent Bus

What it does

The skill is a router for the single `metabot` command line of MetaBot Personal Edition, which replaces the retired `mm`, `mh` and `mb` binaries. It covers CLI and durable-state behavior only, while project execution policy belongs in the workspace `AGENTS.md`. Reference files cover searching, reading, creating, sharing and deleting Meta Memory, browsing and installing skills, inspecting agents and sending durable Agent Bus messages, T5T status, and scheduling or runtime inspection. Agent Teams use a separate `metabot-team` skill.

The CLI talks to a Personal Core at `http://127.0.0.1:9200` by default, overridable with `METABOT_CORE_URL`, and authenticates with `METABOT_CORE_TOKEN` or the first line of `~/.metabot-core/token`. `metabot agents whoami` shows the current identity, and `metabot send` returns message, session and run identifiers, with `--session` and `--idempotency-key` available when a retry must target the same run. Global and project skill destinations are separate scopes, and returned IDs should be kept for later recovery.

When your agent uses it

  • Searching or saving notes in MetaBot's shared memory
  • Sending a durable message to another agent over the Agent Bus
  • Installing or publishing a skill through the skill hub
  • Scheduling work or inspecting a MetaBot runtime

Example prompts

  • “Search my MetaBot memory for notes about the billing migration.”
  • “Send the research agent a durable message asking for the latest competitor summary.”
  • “List the skills available in the skill hub.”

Requirements

  • The `metabot` CLI and a running MetaBot Personal Core
  • `METABOT_CORE_TOKEN`, or a token file at `~/.metabot-core/token`

What it can do on your machine

Read from SKILL.md and the folder at commit 916637e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • METABOT_CORE_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MetaBot CLI loads about 573 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~573
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xvirobotics/metabot at commit 916637e, republished under its MIT licence (© xvirobotics). 215 words, ~573 tokens.

Download SKILL.mdSave it as .claude/skills/metabot/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
metabot
description
Unified MetaBot CLI for personal Memory, Skill Hub, durable Agent Bus messaging, agent registry, Agent Teams, T5T, scheduling, and bridge runtime operations.

MetaBot Personal CLI Router

metabot is the single CLI for MetaBot Personal Edition. Legacy mm, mh, and mb binaries are retired. This Skill documents CLI and durable-state semantics only; project execution policy belongs in the workspace AGENTS.md.

Command References

SurfaceReference
Search, read, create, update, share, or delete Meta Memoryreferences/memory.md
Browse, install, or publish a Skillreferences/skills.md
Inspect Agents or send durable Agent Bus messagesreferences/agents.md
Coordinate an Agent TeamUse the separate metabot-team Skill
Read or write T5T statusreferences/t5t.md
Schedule work or inspect a runtimereferences/runtime.md

Fast Path

bash
metabot memory search "query"
metabot memory get <id|path>
metabot skills list
metabot agents list
metabot send <agentId> "message"
metabot teams status <team> --summary
metabot t5t push <project> <YYYY-MM-DD> "entry"
metabot health

Run metabot help or metabot <surface> --help before assuming an optional bridge-local command is available.

Authentication And Scope

  • Personal Core defaults to http://127.0.0.1:9200.
  • Override it with METABOT_CORE_URL for another user-configured Core.
  • Use METABOT_CORE_TOKEN, or the first line of ~/.metabot-core/token.
  • metabot agents whoami shows the current Core identity.
  • metabot send returns durable messageId, sessionId, and runId values; pass --session or --idempotency-key when a retry must target the same logical run.
  • Project and global Skill destinations are distinct discovery scopes.
  • MetaBot's own metabot and metabot-team bundles are global-only; project mirrors are retired outside discovery roots so stale copies cannot shadow updates.

Output

Commands may return document IDs, paths, message IDs, Task IDs, Run IDs, and session IDs. Preserve the identifiers needed for later inspection or recovery.

© xvirobotics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in packages/skills/metabot of xvirobotics/metabot.

  • SKILL.md
  • references/agents.md
  • references/memory.md
  • references/runtime.md
  • references/skills.md
  • references/t5t.md

Open the folder on GitHubat commit 916637e

Compare with similar skills

MetaBot CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MetaBot CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MetaBot CLI this skillxvirobotics/metabot994—~573Automated safety check: PassMIT
Munder Difflin Hive SyncHarnessMD/munder-difflin8.6k—~331Automated safety check: NotesMIT
Autonomous Agent Harnessaffaan-m/ECC276k2 repos~2.9kAutomated safety check: PassMIT
SkillOpt Sleep Cyclemicrosoft/SkillOpt18k—~2.3kAutomated safety check: PassMIT
SkillOpt-Sleep Self-Improvement Cyclemicrosoft/SkillOpt18k—~2.3kAutomated safety check: PassMIT
OpenClaw to NanoClaw Migrationnanocoai/nanoclaw31k—~6kAutomated safety check: NotesMIT

Similar skills

  • Munder Difflin Hive Sync

    HarnessMD/munder-difflin

    Runs the start-of-task routine for an agent working in a multi-agent hive: reads memory.md, processes new inbox messages and reminds the agent to record durable facts before ending.

    8.6k GitHub stars~331 tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.

    276k GitHub starsUsed in 2 repos~2.9k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Official

    Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.

    18k GitHub stars~2.3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Guides a conversational migration from an OpenClaw install to NanoClaw v2, carrying over identity, channel credentials, scheduled tasks and workspace files.

    31k GitHub stars~6k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check: notes
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs a usage-driven self-improvement cycle for the dsh agent: harvest past sessions, mine recurring tasks, replay them and stage validated skill edits.

    18k GitHub stars~1.4k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from xvirobotics/metabot

  • Generates Chinese speech audio from text using Volcengine's Doubao TTS API, for narration, voiceovers or multi-voice podcasts.

    994 GitHub stars~1.1k tokensUpdated 24 days ago
    Auto-check: notes
  • MetaBot Agent Teams CLI

    xvirobotics/metabot

    Documents the metabot teams command surface for creating durable teams, spawning teammates, dispatching tasks and inspecting their runs across engine sessions.

    994 GitHub stars~693 tokensUpdated 24 days ago
    Auto-check passed
  • MetaBot Scheduler

    xvirobotics/metabot

    Schedules persistent cron and one-shot tasks on the MetaBot server that survive Claude session restarts and can be managed by other bots.

    994 GitHub stars~1k tokensUpdated 24 days ago
    Auto-check passed
  • Agent Team And Skill Builder

    xvirobotics/metabot

    Decides whether a request wants a full agent team, one agent, or one skill, then follows the matching flow file to generate it.

    994 GitHub stars~628 tokensUpdated 24 days ago
    Auto-check: notes

Questions about MetaBot CLI

What does MetaBot CLI do?

Documents the unified `metabot` CLI for personal memory, the skill hub, durable agent messaging, the agent registry, T5T status and scheduling. The skill is a router for the single `metabot` command line of MetaBot Personal Edition, which replaces the retired `mm`, `mh` and `mb` binaries.md`.

When should I use MetaBot CLI?

MetaBot CLI fits situations like: searching or saving notes in MetaBot's shared memory; sending a durable message to another agent over the Agent Bus; installing or publishing a skill through the skill hub; scheduling work or inspecting a MetaBot runtime.

How do I install MetaBot CLI in Claude Code?

Run `npx skills add xvirobotics/metabot --skill metabot -a claude-code`. Or copy the skill folder (packages/skills/metabot in xvirobotics/metabot) into .claude/skills/metabot in your project. Claude Code loads it when a task matches its description.

How do I install MetaBot CLI in Codex?

Run `npx skills add xvirobotics/metabot --skill metabot -a codex`. Or copy the skill folder (packages/skills/metabot in xvirobotics/metabot) into .agents/skills/metabot in your project. Codex loads it when a task matches its description.

Can I use MetaBot CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xvirobotics/metabot --skill metabot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/metabot, .gemini/skills/metabot, .github/skills/metabot and .opencode/skills/metabot in your project.

What does MetaBot CLI need to run?

Going by SKILL.md and its folder, MetaBot CLI needs credentials named METABOT_CORE_TOKEN. Our summary lists: The `metabot` CLI and a running MetaBot Personal Core; `METABOT_CORE_TOKEN`, or a token file at `~/.metabot-core/token`.

Does MetaBot CLI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MetaBot CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MetaBot CLI use?

MetaBot CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MetaBot CLI use?

About 573 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 693 tokens, read only when the agent opens those files.

What are the alternatives to MetaBot CLI?

Skills that share tags, products or a category with MetaBot CLI: Munder Difflin Hive Sync (HarnessMD/munder-difflin, 8.6k stars), Autonomous Agent Harness (affaan-m/ECC, 276k stars), SkillOpt Sleep Cycle (microsoft/SkillOpt, 18k stars) and SkillOpt-Sleep Self-Improvement Cycle (microsoft/SkillOpt, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MetaBot CLI?

xvirobotics (a GitHub organization) maintains it in xvirobotics/metabot, which has 994 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 15, 2026.

Source: xvirobotics/metabot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.