Hanzo Dev

Slash Commands

All built-in slash commands available in the Hanzo Dev TUI.

Hanzo Dev supports slash commands in the TUI composer. Commands marked "prompt-expanding" transform your input into a full prompt and typically kick off multi-agent flows.

CommandDescription
/browserOpen internal browser
/chromeConnect to your Chrome browser
/newStart a new chat during a conversation
/resumeResume a past session for this folder
/quitExit Hanzo Dev
/logoutLog out
/loginManage sign-ins (select, add, or disconnect)
/settings [section]Open settings panel (optional: model, theme, agents, skills, auto, review, validation, limits, chrome, mcp, notifications)

Workspace & Git

CommandDescription
/initCreate an AGENTS.md file with instructions
/diffShow git diff (including untracked files)
/undoOpen snapshot picker to restore workspace files
/branch [task]Create a worktree branch and switch to it
/mergeMerge current worktree branch back into default
/pushCommit, push, and monitor workflows
/review [focus]Open review picker or review with focus text
/cloudBrowse Cloud tasks from the TUI
/cmd <name>Run a project command for the current workspace

UX & Display

CommandDescription
/themeCustomize the app theme
/verbosity (high|medium|low)Change text verbosity
/modelChoose your default model
/reasoning (minimal|low|medium|high)Change reasoning effort
/promptsManage custom prompts
/skillsManage skills
/statusShow session configuration and token usage
/limitsAdjust session limits and rate-limit usage
/updateCheck version and run guided upgrade
/notifications [status|on|off]Manage notification settings
/mcp [status|on|off \<name\>|add]Manage MCP servers
/validation [status|on|off]Inspect or toggle validation harness

Search & Mentions

CommandDescription
/mentionMention a file (opens file search)

Performance & Agents

CommandDescription
/perf (on|off|show|reset)Performance tracing controls
/agentsConfigure agents and subagent commands
/auto [goal]Start the Auto Drive coordinator

Prompt-Expanding (Multi-Agent)

These commands expand into full prompts and start multiple agents. They require a task/problem description.

CommandDescription
/plan <task>Create a comprehensive plan (multiple agents)
/solve <problem>Solve a challenging problem (multiple agents)
/code <task>Perform a coding task (multiple agents)

On this page