Prepare a Lola module for Che workspaces
Prepare a Lola module in a Git repository so that Che installs its AI assistant skills, commands, and agents into workspaces at startup.
Lola reads the module and writes its content into the native directory structure of each AI assistant that you install it for. Prepare one module for every assistant that your team uses, rather than one module per assistant: the skills, commands, agents, and instructions are the same, and only the destination directory differs.
-
A Git repository for the module that workspaces can reach. Prefer a public repository, because a workspace can clone a private repository only when it has Git credentials configured.
-
uvon the workstation that prepares the module, to install the Lola command-line tool. See uv. -
Lola on the workstation that prepares the module, at the commit the init image pins. The released version predates the agent-plugin layout, so install the commit rather than the package:
$ uv tool install "git+https://github.com/LobsterTrap/lola@53b3687975b373c856fc67b9a8f18c395c76fca4"
-
Create the module structure in the repository root. Lola takes the module name from the
namefield ofplugin.json, so keep that field equal to the repository directory name. A name argument tolola mod initwould create a subdirectory instead:$ lola mod init -s <skill-name>
The command creates the agent-plugin layout with example content:
plugin.json README.md mcp.json skills/<skill-name>/SKILL.md dev.getlola/ AGENTS.md agents/example-agent.md commands/example-command.md
--minimalomits the example content, but it still writesREADME.mdandplugin.json, and creates the empty component directories. You can also create the same files by hand. -
Set the module name, version, and description in
plugin.json. Keep thedev.getlolaextension so that Lola finds the commands, agents, and instructions:{ "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json", "name": "my-agent-config", "version": "0.1.0", "description": "Team AI assistant configuration.", "extensions": { "dev.getlola": { "commands": "./dev.getlola/commands", "agents": "./dev.getlola/agents", "instructions": "./dev.getlola/AGENTS.md" } } } -
Add skills. Each skill is a directory under
skills/that contains aSKILL.mdfile. Lola discovers every skill directory automatically, so the manifest does not list them:--- name: review-checklist description: "Review checklist for a Go change: tests, error handling, and rollback." --- # Review checklist Describe when the assistant uses this skill and what it must do.
-
The file starts with a YAML front matter block.
-
The
descriptionfield is mandatory. Lola skips a skill without a description and reports a warning. -
Quote a description that contains a colon. Without quotes the front matter is invalid and Lola skips the whole skill.
-
-
Optional: Add commands and agent definitions as Markdown files under
dev.getlola/commands/anddev.getlola/agents/. Each file has adescriptionfield in the front matter. -
Optional: Add MCP servers to
mcp.json. Usetype: streamable-httpfor a remote server. Do not add credentials: the file is stored in Git and copied into the workspace. -
Validate the module before you push it.
lola mod add .reports the same warnings that the init container reports at workspace startup:$ lola mod add . $ lola install <module-name> -a <assistant> -s user
Check that the content is present in the destination of that assistant and that no warning names a skill or an agent.
-
Validate the module for the other assistants that your team uses. One module serves every assistant: run the command from the previous step once per assistant, or run it without
-ato select the assistants interactively:$ lola install <module-name> -s user
-
-aaccepts a single assistant, for example-a gemini-clior-a opencode. Run the command once per assistant in the subset that you want to check. -
Without
-a, Lola asks which assistants to select, because the command runs in a terminal. The init container runs without a terminal and installs Lola’s default set, which leaves outcopilot-cli. -
openclawneeds a different command:lola install <module-name> -a openclaw -s userfails with--scope user cannot be used with a project path argument. Run it without-s user. OpenClaw installs into/home/user/.openclaw/workspace, so create that directory first if it does not exist, and it receives the skills only, because Lola drops commands, agents, and MCP servers for that assistant. The init container creates that directory and runs this command itself, so namingopenclawinLOLA_AGENTSworks. -
Each assistant receives the content in its own location. See AI assistant configuration reference.
-
Gemini CLI has no agent definitions: Lola skips the files in
dev.getlola/agents/for that assistant and converts commands to the TOML format. -
Che installs the module for the assistants that the
LOLA_AGENTSvariable names, as a single name, a comma-separated list, orall. Check the module with the same list that your workspaces use. See Install the recommended AI assistant configuration in every workspace.
-
-
Commit and push the module. Create a tag for each release so that clusters can install a fixed version.
-
lola listshows the installed modules and the assistants they are installed for.lola mod info <module-name>lists the skills that Lola found in the module. -
A workspace started with the recommended configuration reports
warnings=0in/home/user/.lola/init-status.