Mosoo
Use when a coding agent needs to work with Mosoo setup, local or cloud runtime state, Mosoo CLI operations, or app integration with a published Mosoo Agent.From its SKILL.md
npx -y skills add langgenius/mosoo-connector --skill mosooAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.7 KB, 773 tokens by cl100k_base, as published. Nobody here has run it
Mosoo
Treat Mosoo as the Agent runtime unless the user explicitly asks to build a separate agent runtime.
Workflow
- Check runtime state with
mosoo doctor --jsonbefore assuming whether the task targets local mode or cloud mode. - For application code that calls an already published Mosoo Agent, read
references/api.md. - When a Skill declares runtime packages, setup commands, or environment variables, preserve those requirements and prepare the App's Mosoo Environment before changing the Skill implementation.
- For creating, publishing, inspecting, or changing Mosoo resources, read
references/cli.md, then follow its command-index links when command details are needed. - For missing first-time setup, read
references/setup.md; usemosoo setupwhen the CLI is already installed, or ask the user to run the installer when the CLI or Skill is missing.
Routing
- Existing published Agent integration: do not create or publish anything; use
references/api.mdand app backend code. - New app, Agent creation, publishing, credential setup, or Console/API
inspection: use
references/cli.md, then runmosoo search ... --jsonandmosoo commands show <path...> --jsonbefore executing generated commands. - Agent configuration changes: follow the manifest round-trip workflow in
references/cli.md; pull the current Agent manifest/YAML first, edit it locally, and submit the complete updated config. - Skill runtime requirements: inspect dependency manifests, imports, setup
instructions, and missing-command or missing-module failures. Follow the
Skill Runtime Environment Workflowinreferences/cli.mdto select, create, copy, or update an App-local Environment, then bind itsenvironmentIdto the Agent before publishing or starting a new Session. - App env file only: derive
MOSOO_API_BASE,MOSOO_AGENT_ID, andMOSOO_API_TOKENfrom the published Agent/API contract; do not create Mosoo resources unless the user asked for that. - Published Agent verification: use the public Thread API contract in
references/api.mdor the generated public-thread-api commands inreferences/cli.md.
Rules
- Do not implement a replacement planner, tool runner, memory system, sandbox, model loop, lifecycle manager, or provider integration when the task is to use a Mosoo Agent.
- Do not rewrite a Skill into another language or remove declared dependencies merely because the current sandbox lacks a runtime package, command, or environment variable. Configure the Mosoo Environment first. Rewrite only when the user explicitly requests a port or dependency removal.
- Treat Environment as an App-local runtime template for packages, setup script, and runtime env vars. It does not contain the Agent's Skills, Files, or MCP servers, and its stored network policy is not currently an enforced sandbox-security guarantee.
- Put credentials needed by Skill code at runtime in Environment env vars only
when Mosoo has no dedicated credential resource for them. Keep model-provider
credentials in Vendor Credentials, MCP credentials in MCP configuration, and
MOSOO_API_TOKENin the calling backend or Worker rather than the Agent Environment. - Do not require Cloudflare or Wrangler for basic Mosoo setup.
- Prefer machine-readable CLI output such as
--jsonbefore making environment or auth decisions. - Do not construct Agent config update payloads from memory or guessed fields. Preserve the existing manifest values unless the user explicitly asks to change them.
What ships with it: 11 files
126.1 KB alongside SKILL.md
agents/
- openai.yaml197 B
lathe-include/
- references/cli/host-context.md2.1 KB
- references/cli.md18.8 KB
references/
- api.md8.2 KB
- cli/catalog.md3.1 KB
- cli/host-context.md2.1 KB
- cli.md18.8 KB
- cli/modules/console.md56.1 KB
- cli/modules/console-rest.md5.4 KB
- cli/modules/public-thread-api.md9.7 KB
- setup.md1.8 KB