How commands work

OpenCode Team defines 19 slash commands in commands/*.md. Run them directly in OpenCode.

Pipeline control

Command	What it does
/team	Start or continue the pipeline
/team-status	Which stages are done, what's next, where you're blocked
/team-next	Run the next stage
/team-approve	Approve the current gate and continue
/role	List the team and which stage each role owns

Stage commands

Each pipeline stage has a direct command: /research, /prd, /backlog, /ux, /brand, /architecture, /build, /qa, /security, /docs, /release and /launch. The command runs the stage even when you are not driving the full pipeline.

Memory commands

Command	Agent	What it does
/memory	orchestrator	Inspect, seed, or compact project-local memory
/remember	active agent	Append a note to the active agent's memory log

/memory arguments:

• status (default): read-only summary of INDEX.md, log sizes, latest decisions, and open questions.
• init: create the memory tree and missing logs; never overwrite existing content.
• compact: archive overflow log lines and shrink INDEX.md; refuse when subagents are active.

/remember appends one short note to the currently active agent's own log. Creates a decisions/ file when the note is a decision. Refuses secrets and raw transcripts.

Installation

Installation is not a slash command. Run ./install.sh from the repository, or see Install.

Full list

Command reference — generated from frontmatter: command, description and target agent.