Modly Cli logo

Modly Cli

CommunityPopular
lightningpixel
modly-cli

Use when an agent needs to call a running Modly desktop instance from the terminal to generate/export image-to-3D assets through canonical JSON-first automation commands.

Overview

Publisherlightningpixel
Repositorymodly
Skill namemodly-cli
Stars
7.6K
Forks
716
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Modly Cli 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.
  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/lightningpixel/modly.git /tmp/modly
mkdir -p .claude/skills
cp -r /tmp/modly/tools/modly-cli .claude/skills/modly-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Modly Cli 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 Modly Cli 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 Modly Cli 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.

Modly CLI

Overview

Modly exposes a local API at http://127.0.0.1:8765 while the official desktop app is running. The stdlib-only CLI at tools/modly-cli/agent.py is an agent helper over the canonical automation contract:

  • health
  • model
  • workflow-run
  • capability
  • process-run

Final machine-readable JSON is printed to stdout. Progress JSON lines, when requested, are printed to stderr.

Prerequisites

Launch the official Modly desktop app first, then check readiness:

bash
python tools/modly-cli/agent.py health

Use --compact when another agent needs single-line JSON:

bash
python tools/modly-cli/agent.py --compact health

GET /health is checked before business operations. If the app is unavailable, failures are structured:

json
{
  "ok": false,
  "code": "API_UNAVAILABLE",
  "message": "Cannot reach Modly API at ..."
}

Canonical Commands

Inspect models through /model/*:

bash
python tools/modly-cli/agent.py model list
python tools/modly-cli/agent.py model status
python tools/modly-cli/agent.py model params --model active

Start or resume workflow runs:

bash
python tools/modly-cli/agent.py workflow-run start --image ./input.png --wait
python tools/modly-cli/agent.py workflow-run status <run_id>
python tools/modly-cli/agent.py workflow-run cancel <run_id>

Generate from an image and export the finished mesh:

bash
python tools/modly-cli/agent.py generate \
  --image ./input.png \
  --output ./export.glb \
  --progress

generate is a friendly wrapper around POST /workflow-runs/from-image and GET /workflow-runs/{run_id}. It does not silently fall back to /generate/*. The JSON includes recovery metadata:

json
{
  "ok": true,
  "run": {"kind": "workflowRun", "id": "..."},
  "workspace_path": "Default/model.glb",
  "export_path": "/absolute/path/to/export.glb",
  "meta": {
    "status_command": "python tools/modly-cli/agent.py workflow-run status ...",
    "cancel_command": "python tools/modly-cli/agent.py workflow-run cancel ...",
    "legacy": false
  }
}

Use --no-export when the caller only needs the workspace path. The hidden export helper remains available to download an existing workspace mesh, but it is not part of the canonical root command set:

bash
python tools/modly-cli/agent.py export --path Default/model.glb --output ./model.glb

Discover capabilities or process runs only when the running server exposes the canonical contract:

bash
python tools/modly-cli/agent.py capability list
python tools/modly-cli/agent.py process-run status <run_id>

If the contract is absent, the CLI fails closed:

json
{
  "ok": false,
  "code": "UNSUPPORTED_PROCESS",
  "message": "This process is not available through the canonical process-run contract."
}

Model Selection

--model auto uses the active model reported by /model/status, then validates that id against /model/all. Explicit --model values are also validated against /model/all. The CLI does not infer hidden capabilities from model names, labels, or string fragments.

Legacy Compatibility

The old /generate/* endpoints are explicit compatibility commands:

bash
python tools/modly-cli/agent.py legacy job <job_id>
python tools/modly-cli/agent.py legacy cancel <job_id>
python tools/modly-cli/agent.py legacy generate --image ./input.png --output ./legacy.glb

Legacy responses include meta.legacy: true. Top-level job, cancel, models, and params aliases may still parse for older scripts, but they are not the documented canonical surface.

Developer-Only API Helpers

Headless startup helpers live under dev:

bash
python tools/modly-cli/agent.py dev serve-api --print-command
python tools/modly-cli/agent.py dev ensure-server
python tools/modly-cli/agent.py dev ensure-server --start --detach

These commands start or inspect only the FastAPI backend. They do not imply Electron/Desktop bridge readiness, scene operation readiness, extension process execution readiness, or full workflow support. Prefer launching the official desktop app for real agent workflows.

Experimental ComfyUI Helpers

ComfyUI orchestration is outside the canonical Modly contract and lives under experimental:

bash
python tools/modly-cli/agent.py experimental comfy-image \
  --workflow Trellis2Workflow \
  --prompt "clean object render, isolated on white" \
  --comfy-output ./source.png

python tools/modly-cli/agent.py experimental generate-from-workflow \
  --workflow Trellis2-Full \
  --prompt "clean orthographic product render of a stylized robot toy" \
  --output ./export.glb

experimental generate-from-workflow --workflow <name> --output <path> treats --output as the final artifact location. If the ComfyUI history contains a downloadable .glb, .gltf, .obj, .stl, or .ply, the CLI downloads that asset directly and does not call Modly health or generation. If the workflow only produces an image, the CLI downloads that image and falls back through the canonical Modly workflow-run generation path. If no supported asset or image is found, it fails with code: "NO_WORKFLOW_OUTPUT".

Hidden Helper Aliases

The top-level status, export, and batch helpers remain parseable for older scripts and agent ergonomics, but root help does not present them as canonical automation primitives. Prefer health, model, workflow-run, capability, and process-run when documenting the supported contract.

Batch Workflow

The hidden batch helper generates meshes sequentially from a directory or manifest JSON through the canonical generate path:

bash
python tools/modly-cli/agent.py batch \
  --input-dir ./images \
  --output-dir ./meshes \
  --continue-on-error

python tools/modly-cli/agent.py batch \
  --manifest ./jobs.json \
  --output-dir ./meshes

Manifest files may be a JSON list, or an object with jobs or images. Each entry can be a string image path or an object with image, optional output, and optional format.

Verification Checklist

  • python tools/modly-cli/agent.py health returns ok: true.
  • python tools/modly-cli/agent.py model list returns model entries.
  • python tools/modly-cli/agent.py generate --image <image> --output <mesh> returns ok: true, run.kind: workflowRun, and recovery metadata.
  • The reported export_path exists and has non-zero size when export is enabled.
  • python tools/modly-cli/agent.py workflow-run status <run_id> can resume polling from metadata.
  • python tools/modly-cli/test_agent.py passes.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Modly Cli AI skill do?

Use when an agent needs to call a running Modly desktop instance from the terminal to generate/export image-to-3D assets through canonical JSON-first automation commands.

Why use Modly Cli on TypingMind?

Because you install it once and use it with any model. Modly Cli 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 Modly Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lightningpixel/modly/tree/main/tools/modly-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Modly Cli?

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 Modly Cli?

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

Is the Modly Cli AI skill free?

Yes. It is published on GitHub by lightningpixel 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 👇