Plan first.
Use `/plan` when the task touches files, carries risk, or needs user review.
Control the real agent runtime without leaving the TUI or Mac canvas.
Control the real agent runtime without leaving the TUI or Mac canvas.
/mode safe/mode auto/mode paranoid| Trigger | Description | Example |
|---|---|---|
| /plan | Enter read-only architecture mode and draft a reviewable plan. | /plan add tests for auth. |
| /goal | Start or control a long-running objective with criteria and evidence. | /goal migrate js to ts. |
| /memory | Open, add, remember, pin, unpin, or delete runtime memory. | /memory pin use vitest. |
| /auth | Open authentication and provider state. | /auth |
| /mcp | Manage MCP servers. | /mcp install github. |
| /subagent | List, launch, fork, or inspect scoped subagents. | /subagent reviewer. |
| /replay | Open session, goal, provider, tool, approval, and memory evidence. | /replay latest. |
| /mode | Switch permission mode for the session. | /mode paranoid. |
| /provider | Switch model route. | /provider openai. |
| /model | Switch or inspect the current routed model. | /model qwen3-coder. |
| /verify | Run configured checks or plan verification. | /verify. |
| /diff | Show the current workspace diff. | /diff. |
| /undo | Back out the last accepted write batch when supported. | /undo. |
| /commit | Prepare a commit message after verification. | /commit. |
Use `/plan` when the task touches files, carries risk, or needs user review.
Use `/goal` when the work has clear completion criteria and may take multiple loops.
Use `/memory` to inspect what the agent will retrieve, and `/replay` to verify what the agent actually used.
Use `/subagent` when investigation, review, tests, browser checks, or docs can happen in parallel.
| Command | Use |
|---|---|
| /diff. | Show the current workspace diff. |
| /verify. | Run configured checks or the checks named in the plan. |
| /undo. | Back out the last accepted write batch when supported. |
| /commit. | Prepare a commit message after verification. |
Mode commands change how much Picasso can do without asking. Sponsor commands explain or block labeled sponsor surfaces. Memory, replay, provider, and subagent commands expose runtime state instead of hiding it behind chat. These choices stay visible in the TUI and Mac app so the current boundary is never implied.
/mode safe/mode auto/mode paranoid/memory/replay latest/subagent/sponsors why/sponsors block <sponsor>The Mac app does not run a separate product. Its screens for memory, plans, goals, replay, modes, approvals, providers, MCP, and subagents call the same local helper and runtime state as the CLI/TUI.
Mac memory writes appear in CLI and TUI memory views.
Goal start, pause, resume, cancel, and replay share the same backend ledger.
Write approvals and destructive confirmations keep the same policy semantics.
Non-interactive command equivalents.
Project-level policy around command execution.
Permission modes, sandboxing, and audit logs.
Picasso for Mac is almost here — a coding agent that looks the way serious tools should, and costs what creative freedom should: nothing. Leave your email and be first on the canvas.
Sponsors and labs — the early canvas is yours. Choose Sponsor or Lab above and we'll reach out before launch.