Agents
Agents, skills and the build catalog
Beyond workflows, Agents keeps everything a workflow builds on: agents, skills, sandboxes, gateways, model policies and more. Each is a versioned resource like a workflow, made and changed in SpudSuite and synced to your runners.
One editor for everything
Every kind in the sidebar under Build and Organisation opens the same way: a list, and an editor with three tabs.
- Form: the settings, with help for each one. SpudSuite checks it as you type.
- YAML: the same thing as text. Edits here change the form.
- History: every version, who saved it and what changed. Restore saves an old version again as a new one.
Save with Save or Ctrl S. Names are lowercase letters, digits and dashes, unique in the workspace, and can't be changed later, because other resources use them by name.
Agents
An agent is a reusable worker for agent steps: a model, instructions, the tools it may use, the skills it knows, the sandbox it works in and its limits (such as a budget). Name it in a workflow step with agent: triager, and every workflow that uses it gets the same behaviour.
- Provider and model: Claude through the Messages API, Claude Code (
claude -p, for agents that work in a code checkout), or any OpenAI-compatible service. - Tools: SpudSuite's own actions, actions from your connections, and MCP servers.
- Sub-agents: other agents it can hand work to.
Skills and the skill marketplace
A skill is know-how an agent can use: a SKILL.md with instructions, plus any helper scripts or reference files next to it.
- Write your own under Skills.
- Browse the Skill marketplace to import skills from your workspace's skill sources: public GitHub or GitLab repositories in the Agent Skills layout, or a skills registry. An imported skill is an ordinary skill, labelled with where it came from. Check for updates shows what importing it again would change; Upgrade or Roll back moves between versions.
- Admins add skill sources under Organisation › Skill sources. Check SpudSuite can read it tests one before you save it.
Sandboxes
A sandbox profile says where script and agent steps run on a runner: on the runner itself (local), in Docker, in Kubernetes pods, or in a hosted sandbox. It sets the image, CPU, memory, disk, network access, the working folder and how long it lives.
Gateways and model policies
- A gateway says how model requests reach a provider: directly, or through LiteLLM, Portkey, OpenRouter, Bedrock and others. It names the secret on your runners that holds the key, and any headers to send. For Claude Code agents, a gateway can use an API key or, where allowed, each person's own Claude sign-in on their runner.
- A model policy says which models may be used, and can route easy and hard work to different models.