Skip to main content

Overview

Agents are Claude Code SDK instances running within a workspace’s git worktree. You see every message, tool call, file edit, and cost in real time.

Starting Agents

Start an agent by writing a prompt in a workspace. You can run multiple agents per workspace for parallel tasks. Each message supports per-message overrides:
OptionValuesDescription
ModelDefault, Opus, Opus 1M, Sonnet, HaikuOverride the default model
EffortLow, Medium, High, MaxControl thoroughness
ThinkingOn/OffExtended thinking mode
Fast ModeOn/OffFaster output
Context 1MOn/OffUse 1M context window
Plan ModeOn/OffStep-by-step with approval

Lifecycle Controls

ActionDescription
PauseSuspend the agent, preserving session
ResumeContinue from where it paused
KillTerminate immediately
Resume AllResume all paused agents across workspaces
Rerun AllCreate fresh agents for all workspace slots

Message Queue

When an agent is busy, messages are queued:
  • Queued messages are persisted to SQLite (crash-safe)
  • Auto-delivered when the agent becomes available
  • Can be cancelled or force-delivered
  • Each queued message preserves its model/effort/thinking options

Plan Mode

When enabled, agents propose a step-by-step plan before executing:
  1. Agent generates plan steps
  2. You review and approve (or edit)
  3. Agent executes approved steps
  4. Progress tracked per-step

Session Resumption

Agent sessions persist across app restarts:
  • Session IDs stored in state
  • On restart, agents with valid sessions resume automatically
  • Agents without sessions are marked as errored with “Interrupted by app restart”

Token Tracking

Per-agent tracking includes:
  • Input/output token counts
  • Cache creation and read tokens
  • Cost in USD
  • Context window fill percentage
  • Daily aggregate usage