lightningpixel/modly/modly-cli
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install lightningpixel/modly/modly-cliSKILL.md
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:
healthmodelworkflow-runcapabilityprocess-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:
Use --compact when another agent needs single-line JSON:
GET /health is checked before business operations. If the app is unavailable, failures are structured:
Canonical Commands
Inspect models through /model/*:
Start or resume workflow runs:
Generate from an image and export the finished mesh:
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:
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:
Discover capabilities or process runs only when the running server exposes the canonical contract:
If the contract is absent, the CLI fails closed:
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:
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:
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:
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:
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 healthreturnsok: true. - [ ]
python tools/modly-cli/agent.py model listreturns model entries. - [ ]
python tools/modly-cli/agent.py generate --image <image> --output <mesh>returnsok: true,run.kind: workflowRun, and recovery metadata. - [ ] The reported
export_pathexists 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.pypasses.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtools/modly-cli/SKILL.md
Popularity
- Repository stars
- 4,214
- Repository forks
- 452
- 7-day trend score
- 42
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lightningpixel/modly/modly-cli)