Are you an LLM? Read llms.txt for a summary of the docs, or llms-full.txt for the full context.
Skip to content
Using the harness

Interactive TUI

Running minima with no prompt opens the interactive terminal UI: a scrolling conversation view, an input prompt, and a status bar. Type a message and press Enter to send it; the harness routes it, runs the chosen model, streams the reply, and executes any tool calls (asking permission where required).

The status bar

The bar along the bottom shows, at a glance:

  • Model — the pinned model, or auto when Minima is routing.
  • Cost — running total from the cost meter for this session.
  • Context — percentage of the model's context window used, plus token counts.
  • State — whether a turn is in flight, plus plan/verification state when plan verification is active.

Keyboard shortcuts

KeyAction
EnterSend the current prompt
/ Cycle input history (at the prompt) · navigate items (in a picker)
Alt+/Jump by word (also Alt+B/F)
Ctrl+A / Home·EndLine start / start·end
Ctrl+K / Ctrl+UKill to end / to start of line
Ctrl+WKill the previous word (also Alt+Backspace)
Ctrl+VPaste clipboard (terminal paste also works)
Ctrl+YCopy the last assistant reply
Esc / Ctrl+CAbort the in-flight run (Ctrl+C twice at the prompt quits)
Ctrl+ZSuspend to the shell (fg returns)
Shift+TabCycle permission modes (build → accept → plan → bypass)
Ctrl+LOpen the model picker
Ctrl+POpen the command palette (slash commands)
Ctrl+RToggle route mode (auto ↔ confirm)
Ctrl+EToggle thinking display
Ctrl+TTable of contents
Ctrl+GPlan Overview
Ctrl+BToggle the task panel
TabAuto-complete a slash command
ℹ️Note

Scrolling, text selection, and copy are native to your terminal (wheel/trackpad) — the TUI doesn't capture the mouse. In pickers, use / to move, Enter to choose, Esc to dismiss.

Slash commands

Type / (or open the palette with Ctrl+P) and pick a command:

Routing & cost

CommandWhat it does
/modelSelect or pin a model (or auto to unpin and let Minima route)
/costShow cost-meter totals
/budgetShow/set the session budget (/budget set <usd> · /budget mode warn|enforce)
/judge [on|off]Toggle LLM quality judging
/reconnectReconnect the routing client

Planning & verification

CommandWhat it does
/planPlan mode (Shift+Tab) + the planning council (start · status · finalize · cancel) — drafts a plan whose steps carry verify checks
/modeShow/set the permission mode: build | accept | plan | bypass
/bpShow Plan Overview status
/why [n]Show the verification evidence behind the plan (or open step n's card)
/verifyAdversarial whole-plan verification pass (refutation sub-agent)
/auditLint the active plan — non-discriminative checks, missing allowlists, vague steps
/tasksToggle the task panel (Ctrl+B) · /tasks cancel rejects the list + the plan
/treeToggle the live sub-agent tree panel

Memory

CommandWhat it does
/memoryCurated memory: list · add <text> · pin/confirm/reject/delete <n|id> · dream — see the memory ledger

History & recovery

CommandWhat it does
/undoUndo the last change — checkpoint restore + re-prompt (stacks)
/rewind [n]Rewind to an earlier prompt (picker, or /rewind <n> [convo|code|both])
/ckptList git-shadow checkpoints (/ckpt gc prunes old runs' refs)
/new · /resume [id]Start fresh · resume a previous session
/name <label> / /renameName this session (persisted)
/sessionShow session info
/compactSummarize old turns to free context

Setup & misc

CommandWhat it does
/authSign in to Mubit & provision this repo's project
/configShow/set API keys (MUBIT, GEMINI, ANTHROPIC, …)
/permsShow current tool permission grants
/thoughts [on|off]Toggle streaming the model's thinking
/copyCopy the last assistant reply (Ctrl+Y)
/clear · /help · /tipClear chat · list commands · show a tip
/quit, /exitExit the application
💡Tip

/model auto hands routing back to Minima after you've pinned a model. Shift+Tab cycles the permission modes — plan lets the agent read and design without touching files, accept auto-approves edits, bypass skips prompts entirely (trusted repos only).

Related