Plugin or skill
The repository ships in two shapes. Pick the one your host supports.If you only need the Agent Skill, see the Skill guide, which covers the standalone
modellix-skill repository as well.What the plugin provides
- A CLI-first workflow:
modellix-cli doctor→model run --wait→task download - Automatic REST fallback when the CLI is not installed
- Sensible default models when you do not name one
- Model discovery through
modellix-cli model listandmodel describe, plus the live model index at llms.txt - Retry and error guidance aligned with CLI exit codes, including paid-submission safety rules
- Credential handling for
MODELLIX_API_KEYand saved CLI auth profiles
Requirements
- A Modellix API key from the Modellix Console
- Recommended:
modellix-clion Node.js 18.17 or later
Install as a plugin
- Claude Code
- Codex
- Cursor
- OpenClaw
- Pi
Install:Update:You can also use the
/plugin UI, then run /reload-plugins if the plugin does not appear.For local development against a clone:Install as a skill
When your host has no plugin marketplace, or you only wantskills/modellix, install the Agent Skill instead:
Configure your API key
Every install shape reads the same credential.--api-key, then MODELLIX_API_KEY, then the selected saved profile.
- REST calls always require
MODELLIX_API_KEY. - The CLI can use the environment variable or a saved profile created by
modellix-cli auth loginormodellix-cli init. - In Cursor, you can set the key as the
MODELLIX_API_KEYplugin variable. - In Hermes, prefer
~/.hermes/.envor the secure prompt shown when the skill loads.
Verify the install
Confirm the environment first, then generate one asset end to end.1
Check the CLI and credentials
doctor reports the Node.js version, the API-key source, API connectivity, and your team balance without printing the key.2
Ask your agent to generate something
3
Confirm the output
The agent downloads results into your working directory. To reproduce the same flow manually:
Supported task types
Default models
When you do not name a model, the plugin uses these defaults:
Name any other model in your prompt to override the default. To discover and inspect models:
docs_url returned by model describe, or the links in llms.txt.
How the plugin runs tasks
Understanding these rules helps you predict what your agent will do:- It prefers the CLI when installed, and falls back to the REST API otherwise.
- It uses
model run --waitortask waitinstead of hand-written polling loops. - It never blindly retries a paid
model runafter an unknown submission outcome. It checksmodellix-cli task historyfirst. - It may use the helper scripts bundled in
skills/modellix/scripts/, and falls back to plain CLI commands if a helper fails. - It treats
modellix-cli --helpand the npm package as the source of truth for CLI behavior.
Troubleshooting
Next steps
Skill
Install the Agent Skill on its own.
CLI
Learn the
modellix-cli commands the plugin runs.REST API
Call Modellix directly without the CLI.
Pricing
Review model pricing before running paid tasks.