Claw Mo Manage logo

Claw Mo Manage

Community
LeeJuOh
claw-mo-manage

Manage mo markdown viewer — check status, add/remove patterns and groups, refresh, stop servers, reset. Use when checking mo status, modifying watch patterns, or troubleshooting.

Overview

PublisherLeeJuOh
Repositoryclaude-code-zero
Skill nameclaw-mo-manage
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 Manage 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-manage
  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-manage .claude/skills/claw-mo-manage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claw Mo Manage 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 Manage 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 Manage 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-manage

Interactive management hub for mo markdown viewer. Shows current state and lets the user choose what to do — including a safe "refresh" that re-scans the filesystem without destroying the session.

For config schema, HTTP API, --restart vs --clear semantics, and CLI wrappers (--unwatch, --close): read ${CLAUDE_PLUGIN_ROOT}/references/shared.md

Steps

1. Gather State

Check prerequisite first: command -v mo >/dev/null 2>&1. If missing, tell the user to install and stop.

Then in parallel:

  • mo --status --json — all running servers
  • Read ${CLAUDE_PLUGIN_DATA}/config.json — all configured projects
  • Get current project key: git rev-parse --show-toplevel

For the current project, extract the live group→patterns mapping from the JSON output and compare it against saved config. Mark the session out of sync if they differ.

2. Display Dashboard

mo server status
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
● project-a     :6342  running  docs(12) plans(3) default(2)
● project-b     :6367  running  specs(5)
○ project-c     :6315  stopped

Current project: project-a (:6342)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Match config entries to running servers for accurate status (● / ○). Also list any running servers found by mo --status --json that aren't in config (user may have started them manually).

If the current project's configured mapping and live mapping differ, show an explicit warning:

⚠ current project is out of sync
configured: {docs: [docs/**/*.md], default: [*.md]}
live: {docs: [/abs/path/docs/*.md], default: [/abs/path/*.md]}

what this means:
  - the running mo session is not watching the same patterns as saved config
  - the next `/claw-mo-up` will clear this runtime and rebuild it from saved config

recommended actions:
  - if saved config is correct → Server control → Reset session (or just run /claw-mo-up)
  - if saved config is outdated → Modify patterns/groups (add/remove), or re-run /claw-mo-setup

3. Ask What to Do

Use AskUserQuestion with a two-step approach to stay within the 4-option limit:

First question — category:

Options:
1. Modify patterns/groups (add, remove, rename)
2. Files (add, remove from view)
3. Server control (refresh, stop, reset, restart)

If "Modify patterns/groups" → second question:

Options:
1. Add pattern to a group
2. Remove pattern from a group
3. Add new group
4. Remove group

If "Files" → second question:

Options:
1. Add a file to a group (ad-hoc, like /claw-mo-open)
2. Close a file currently open in mo

If "Server control" → second question:

Options:
1. Refresh (re-scan filesystem, keep session) — runs `mo --restart`
2. Reset current session (clear saved state + restart empty, then rebuild from config)
3. Stop a server
4. Toggle autosync for this project (PostToolUse hook)

If the session is out of sync and the user chose "Modify patterns/groups", recommend Reset first so later changes apply on top of a known-good runtime.

4. Handle Each Action

All runtime mutations should use the mo CLI when there is a CLI equivalent (-w/--unwatch/--close/--restart). Fall back to the HTTP API only when no CLI path exists. Config file updates happen after the runtime mutation succeeds.

Add pattern:

  1. Ask which group (show existing groups)
  2. Ask the glob pattern
  3. If server running: mo --no-open -w "$PATTERN" -t "$GROUP" -p $PORT
    • Otherwise skip the runtime step
  4. Update config file
  5. Confirm

Remove pattern:

  1. Show current patterns per group
  2. Ask which to remove
  3. If server running: mo --unwatch "$PATTERN" -t "$GROUP" -p $PORT
    • mo accepts either the original glob or the absolute path form reported by --status
  4. Update config file
  5. Confirm

Add group: Ask group name and one initial pattern → start it via mo -w ... -t name -p $PORT if running → update config

Remove group: Show groups, ask which → mo --unwatch for every pattern in that group (group disappears when it has no files or patterns) → update config (remove group key)

Add file (ad-hoc): Delegate to /claw-mo-open logic (HTTP API POST to /_/api/groups/$GROUP/files). Warn this is runtime-only unless persisted.

Close a file:

  1. curl -s "http://localhost:$PORT/_/api/groups" → list files in each group
  2. Ask which file
  3. mo --close "$(realpath file)" -t "$GROUP" -p $PORT
  4. No config update needed (ad-hoc file, not a pattern)

Refresh (re-scan):

  1. mo --restart -p $PORT (no prompt, safe)
  2. Verify with mo --status --json and report new file counts
  3. This is the fix when docs exist on disk but don't appear in mo — same mechanism /claw-mo-up uses by default.

Reset session:

  1. printf 'y\n' | mo --clear -p $PORT
  2. Ask: "Restart with saved config now?" (equivalent to /claw-mo-up)
  3. If yes, run the per-group start sequence from config

Stop a server:

  1. Show all running servers (from mo --status --json) with their ports and projects
  2. Ask which to stop (by number or port)
  3. mo --shutdown -p $PORT
  4. Confirm — note that config is preserved so /claw-mo-up can restart it later

Toggle autosync:

  1. Read current autosync field (default true if absent)
  2. Show current state: Autosync is ON — .md writes by Claude are added to mo automatically.
  3. AskUserQuestion: flip it?
  4. Update config file only — no runtime call needed; the hook reads the config on each fire
  5. Confirm new state

5. Loop or Exit

After each action, show the updated dashboard and ask if they want another action. Exit when done.

Gotchas

  • Prefer mo --restart over --clear for rescans — restart preserves session; clear destroys the backup. The old "just clear everything" reflex wipes state that didn't need wiping.
  • Only --clear prompts for confirmation — pipe printf 'y\n'. --restart, --shutdown, --close, --unwatch do not prompt.
  • Config is desired state — always update config AND runtime (CLI or API) together when making a persistent change.
  • Compare full live group→patterns mapping to config before assuming a running server is reusable — matching port or group names alone isn't enough.
  • If session is out of sync, prefer Reset before multiple runtime edits; otherwise stale groups/patterns persist and /claw-mo-up will discard your runtime edits on the next invocation.
  • Group names must be simple lowercase — they become URL path segments.
  • If the server is not running, only update config — skip CLI/API calls.
  • "Close a file" only removes it from the view — the file on disk is untouched and will be re-added if it matches a watch pattern and mo --restart runs.
  • "Stop a server" only stops the process — config and backup are preserved so /claw-mo-up can restart it later.
  • mo --unwatch accepts both relative globs and absolute paths (the form --status shows). Either works.
  • Autosync is read per fire, not cached: flipping it takes effect on the next Write|Edit|MultiEdit — no need to restart mo or reload Claude. The hook re-reads config.json every invocation, so the toggle is effectively live.

Frequently asked questions

What does the Claw Mo Manage AI skill do?

Manage mo markdown viewer — check status, add/remove patterns and groups, refresh, stop servers, reset. Use when checking mo status, modifying watch patterns, or troubleshooting.

Why use Claw Mo Manage on TypingMind?

Because you install it once and use it with any model. Claw Mo Manage 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 Manage 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-manage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Claw Mo Manage?

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 Manage?

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

Is the Claw Mo Manage 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 👇