How agents work

OpenCode Team defines 14 agent roles in agents/*.md. Every role uses mode: all, so it is reachable three ways:

• Tab / Shift+Tab to cycle through agents
• @agent-name to mention one directly
• the orchestrator can launch it as a subagent through the task tool

The orchestrator is the default agent. It routes an idea through the pipeline and asks for approval at each gate. A specialist owns one stage and writes that stage's artifact. In the build stage, fe and be write specialist reports and the orchestrator consolidates them into .team/07-build.md.

Direct invocation

Every agent is reachable directly:

@analyst
@pm
@po
@ux
@brand
@architect
@fe
@be
@qa
@security
@docs
@devops
@marketing

Directly invoked agents follow the same memory protocol as subagents: read .team/memory/INDEX.md and their own log, then write at most 5 lines to their own log.

Adding a role

1. Create agents/<role>.md with frontmatter (name, description, mode: all, model, permission).
2. Reference it in team.yaml as agent: <role>.
3. Add a command in commands/<role>.md if you want a direct entry point.

Full list

Agent reference — generated from frontmatter: name, description, mode and model.