Claw Mo Up logo

Claw Mo Up

Community
LeeJuOh
claw-mo-up

Start or reopen the mo markdown viewer for the current project. Use when mo is already configured and the user wants to view docs, start mo, open documentation viewer, or preview markdown.

Overview

PublisherLeeJuOh
Repositoryclaude-code-zero
Skill nameclaw-mo-up
Stars
53
Forks
4
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by LeeJuOh on GitHub. Read the source before you install it.

Installation

Install the Claw Mo Up AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LeeJuOh/claude-code-zero/tree/main/plugins/claw-mo/skills/claw-mo-up
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LeeJuOh/claude-code-zero.git /tmp/claude-code-zero
mkdir -p .claude/skills
cp -r /tmp/claude-code-zero/plugins/claw-mo/skills/claw-mo-up .claude/skills/claw-mo-up
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claw Mo Up in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Claw Mo Up on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Claw Mo Up is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

claw-mo-up

Bring up the mo markdown viewer for the current project and open the browser. When a server is already running, restart it by default so new files on disk become visible (fsnotify can silently miss events).

For config schema, decision tree, --restart vs --clear semantics, and browser opening: read ${CLAUDE_PLUGIN_ROOT}/references/shared.md

Arguments

  • $ARGUMENTS (optional)
    • --reuse — Skip mo --restart when live matches config. Use this when the running session is known-good and the user explicitly wants zero interruption.

Steps

[!NOTE] With autosync enabled (default), /claw-mo-up is only needed to (a) start mo for the first time in a session, (b) recover from a silent fsnotify miss via mo --restart, or (c) reconcile a drifted runtime to saved config. Routine new-file visibility does not require a restart anymore.

  1. Prerequisites: command -v mo >/dev/null 2>&1. If missing, tell user brew install k1LoW/tap/mo and stop.

  2. Project key: git rev-parse --show-toplevel (fallback: $PWD).

  3. Read config from ${CLAUDE_PLUGIN_DATA}/config.json. If no entry for this project, tell the user to run /claw-mo-setup and stop.

  4. v1 migration: If the entry has patterns instead of groups, migrate to groups format and save back.

  5. Probe server: mo --status --json 2>/dev/null. Extract the server whose port matches $PORT.

  6. Branch on state — see the decision tree in shared.md:

    (a) No server on this port → start per group sequentially:

    bash
    mo --no-open -w 'pattern1' -w 'pattern2' --target groupName -p $PORT
    mo --no-open -w 'pattern3' --target anotherGroup -p $PORT

    (b) Server running, live matches config:

    • Default: mo --restart -p $PORT — fresh fsnotify scan, session preserved. This is the main fix for the "docs exist on disk but don't show up in mo" class of bug.
    • If --reuse flag was passed: skip restart, reuse as-is.

    (c) Server running, live differs from config (treat config as source of truth):

    1. Show a concise diff (groups added/removed, patterns changed) so the user sees why a clear is happening
    2. printf 'y\n' | mo --clear -p $PORT
    3. Start per group as in (a)
    4. Mention that ad-hoc runtime edits were discarded; persist via /claw-mo-manage or /claw-mo-setup next time
  7. Open browser — prefer cmux whenever reachable. $CMUX_SURFACE_ID alone is not a reliable signal:

    • cmux path ($CMUX_SURFACE_ID set OR command -v cmux):

      1. cmux list-pane-surfaces to inspect existing surfaces
      2. If a surface already targets localhost:$PORT, reuse it: cmux browser "surface:N" navigate "http://localhost:$PORT" (keep the surface: prefix)
      3. Otherwise cmux browser open "http://localhost:$PORT" (or open-split for first-time split layout)
    • Fallback: open "http://localhost:$PORT"

  8. Report what actually happened:

    • started / restarted (fresh scan) / reused as-is / cleared + rebuilt (config drift)
    • active groups + file counts (from mo --status --json)
    • the URL

Gotchas

  • Restart is the default because fsnotify can silently miss file creation events (new subdirectories, high load, macOS FSEvents coalescing). mo --restart is cheap (<1s), preserves the session, and forces a full re-scan. The old "reuse silently" behavior hid missing files.
  • Always --no-open when starting mo — the skill controls browser opening separately.
  • Start groups sequentially, not in parallel — the first invocation must start the server before others can add to it.
  • mo auto-restores previous sessions from its backup file. A matching port alone does not guarantee a correct session. Always compare the full live group→patterns mapping to config; if it drifts, clear and rebuild.
  • mo status reports absolute patterns; config stores relative globs. Normalize config patterns to absolute paths under the project root before comparing, and sort within each group so ordering differences don't create false mismatches.
  • mo --restart does NOT prompt — safe to call directly. Only --clear needs printf 'y\n' |.
  • /claw-mo-up is the reconcile point: ad-hoc runtime-only edits belong in /claw-mo-manage or /claw-mo-setup if they should persist.
  • Prefer cmux over open whenever cmux is reachable. $CMUX_SURFACE_ID may be unset even inside a cmux pane (nested shells). Check command -v cmux too.
  • Reuse cmux surface before browser open — open stacks duplicate tabs. Pass the exact identifier (e.g., surface:4, not 4).
  • Autosync vs. /claw-mo-up: the PostToolUse hook handles routine new-file visibility for files Claude writes. /claw-mo-up remains the fix when (a) mo isn't running yet, (b) fsnotify missed something an external editor wrote, or (c) config drifted. Don't run /claw-mo-up as a reflex on every new file — it's cheap but not free.

Related Commands

  • /claw-mo-setup — initial project configuration (patterns, groups)
  • /claw-mo-down — stop the mo server
  • /claw-mo-manage — modify patterns, check status, refresh

Frequently asked questions

What does the Claw Mo Up AI skill do?

Start or reopen the mo markdown viewer for the current project. Use when mo is already configured and the user wants to view docs, start mo, open documentation viewer, or preview markdown.

Why use Claw Mo Up on TypingMind?

Because you install it once and use it with any model. Claw Mo Up is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Claw Mo Up in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeeJuOh/claude-code-zero/tree/main/plugins/claw-mo/skills/claw-mo-up. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Claw Mo Up?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Claw Mo Up?

As many as you like. As long as a model supports skills, you can use Claw Mo Up with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Claw Mo Up AI skill free?

Yes. It is published on GitHub by LeeJuOh under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇