Claw Mo Open logo

Claw Mo Open

Community
LeeJuOh
claw-mo-open

Open a specific markdown file, directory, or piped content in mo. Use when the user wants to quickly view one markdown file, add a file to mo, pipe markdown to the viewer, or preview a specific document.

Overview

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

Use it in TypingMind

Enable Claw Mo Open 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 Open 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 Open 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-open

Add a specific file, directory, or piped markdown content to the running mo server and open the browser directly on that file.

For config schema, HTTP API, deep-linking, and browser opening: read ${CLAUDE_PLUGIN_ROOT}/references/shared.md

Arguments

  • $ARGUMENTS — one of:
    • File path: docs/spec.md
    • Directory: docs/ (added as a watch pattern)
    • - or --stdin: read markdown from stdin (e.g., cat notes.md | /claw-mo-open -)
    • Optional --group <name> to pin the target group (otherwise auto-detected)
  • Examples:
    • /claw-mo-open docs/spec.md
    • /claw-mo-open plans/ --group plans
    • some-tool | /claw-mo-open - --group scratch

Steps

  1. Parse $ARGUMENTS:

    • Detect --stdin or a bare - → stdin mode
    • Otherwise resolve file/dir path with realpath
    • Extract --group; if absent, auto-detect from config (match the file path against each group's patterns, fall back to default)
  2. Prerequisites: command -v mo >/dev/null 2>&1.

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

  4. Read config from ${CLAUDE_PLUGIN_DATA}/config.json.

  5. Check running server: mo --status --json → is a server on $PORT?

  6. If server is running AND config exists — verify sync before mutating:

    • Compare live group→patterns to saved config (see shared.md)
    • If drifted: tell the user that /claw-mo-up would clear+rebuild this runtime; ask whether to resync first or add into the drifted runtime
    • If they resync: clear, restart from config, then continue
    • If they decline: continue but warn the change won't survive the next /claw-mo-up unless config is updated
  7. Add the content based on mode:

    (a) File path, server running:

    bash
    curl -s -X POST "http://localhost:$PORT/_/api/groups/$GROUP/files" \
      -H 'Content-Type: application/json' \
      -d "{\"path\": \"$(realpath file.md)\"}"

    (b) Directory, server running:

    bash
    curl -s -X POST "http://localhost:$PORT/_/api/patterns" \
      -H 'Content-Type: application/json' \
      -d "{\"pattern\": \"$(realpath dir)/**/*.md\", \"group\": \"$GROUP\"}"

    (c) Stdin, server running: mo's single-instance detection pushes stdin content to the running server automatically:

    bash
    cat | mo --no-open -p $PORT -t "$GROUP"

    (d) Server NOT running:

    • Has config → perform /claw-mo-up behavior first (restart if server reappears mid-flight), then retry step 7
    • No config → quick-open with auto-config:
      1. Auto-assign port: echo $((6300 + $(echo "$PROJECT_ROOT" | cksum | cut -d' ' -f1) % 100))
      2. Start mo:
        • File: mo --no-open -p $PORT "$(realpath file.md)"
        • Dir: mo --no-open -p $PORT "$(realpath dir)" (mo converts dir → dir/*.md watch)
        • Stdin: cat | mo --no-open -p $PORT
      3. Save minimal config to ${CLAUDE_PLUGIN_DATA}/config.json:
        json
        { "PROJECT_ROOT": { "port": PORT, "groups": { "default": ["*.md"] } } }
      4. Tell the user: "Saved a minimal config. Run /claw-mo-setup to customize watch groups."
  8. Resolve deep-link URL — try to open directly on the added file, not just the group:

    File mode:

    bash
    FILE_ID=$(curl -s "http://localhost:$PORT/_/api/groups" | python3 -c "
    import sys, json, os
    target = '$(realpath file.md)'
    for g in json.load(sys.stdin):
        for f in g.get('files', []):
            if f.get('path') == target:
                print(f['id']); break
    ")
    URL="http://localhost:$PORT/$GROUP"
    [ -n "$FILE_ID" ] && URL="$URL?file=$FILE_ID"

    Stdin mode: mo generates stdin-<hash>.md. Look up its ID the same way, matching by name prefix stdin-.

    Directory mode: no single file to link to; use http://localhost:$PORT/$GROUP.

  9. Open browser using the cmux-preferred logic from shared.md (reuse existing surface if one targets this port).

  10. Report — what was added (path or stdin-<hash>.md), which group, whether the session was reused/resynced, the resolved URL.

Gotchas

  • HTTP API needs absolute paths — always realpath before sending.
  • Compare live to config before reusing a running session — matching port or group names alone doesn't prove correctness.
  • Drift warning is a feature, not a chore: runtime-only additions get wiped by the next /claw-mo-up unless persisted through /claw-mo-setup or /claw-mo-manage.
  • Directory args ≠ watch patterns at the API layer: the HTTP API requires you to form the glob (dir/**/*.md) explicitly. mo's CLI does that conversion for free when you pass a dir as a positional arg — that's why quick-open uses the CLI form.
  • Deep-linking falls back gracefully: if the file ID lookup fails (file just added, async), opening /GROUP still works and the new file will appear in the sidebar via SSE.
  • Stdin content dedupes by hash: piping the same content twice reuses the existing entry (stdin-<hash>.md).
  • cat | mo requires stdin to not be a TTY. Fine when a pipe is present; fails silently if Claude somehow passes an interactive stdin. The shell pipe cat | mo forces non-TTY.
  • Quick-open saves a minimal config so /claw-mo-up, /claw-mo-down, and /claw-mo-manage can find the session.
  • If the group doesn't exist in mo yet, the API creates it. The group name becomes a URL path segment — keep it simple lowercase.
  • Adding a file already in mo is safe — dedup by path.

Frequently asked questions

What does the Claw Mo Open AI skill do?

Open a specific markdown file, directory, or piped content in mo. Use when the user wants to quickly view one markdown file, add a file to mo, pipe markdown to the viewer, or preview a specific document.

Why use Claw Mo Open on TypingMind?

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

Which AI models can use Claw Mo Open?

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 Open?

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

Is the Claw Mo Open 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 👇