USER MANUAL · REFERENCE

CLI Reference

Complete command reference for the ClawButler CLI (`ap`), including runtime-host discovery and operator workflows.

Installation & Setup#

The ClawButler CLI (command: ap) is a Python tool installed via pip or uv:

bash
# Install with pip
pip install clawbutler-cli

# Or with uv (recommended)
uv pip install clawbutler-cli

# Or run from repo
cd apps/cli && uv run ap --help

After installation, verify with:

Terminal
$ ap --version
clawbutler-cli 0.1.0

Authentication#

Before using any command, authenticate with your ClawButler instance:

Log in with email/password or API token. Creates a stored profile.

Terminal
$ ap auth login

Refresh an expired access token using the stored refresh token.

Terminal
$ ap auth refresh

Clear stored session tokens for one or all profiles.

Terminal
$ ap auth logout

Show the current authenticated user's details.

Terminal
$ ap auth whoami

The CLI supports multiple profiles for switching between instances:

Show all stored profiles

Terminal
$ ap profile list

Switch active profile

Terminal
$ ap profile use <name>

Delete a stored profile

Terminal
$ ap profile remove <name>

Command Tree#

Current top-level commands, grouped to roughly match the Web navigation.

Operate Commands

  • ap dashboardRead dashboard summaries and top-level operational health
  • ap agentList, show, enable, disable, kill-switch, and configure agents
  • ap approvalList, approve, reject, batch-process approvals and manage rules
  • ap kill-switchEmergency stop and recovery (`trigger` / `recover`)
  • ap activityView real-time agent activity feed
  • ap sessionList and inspect agent sessions
  • ap chatStart streaming chat with an agent

Insights Commands

  • ap auditSearch and export audit trail entries
  • ap costView cost summaries, trends, and breakdowns by agent/model/task
  • ap budgetManage budgets, view advice, adopt/dismiss recommendations
  • ap cronList, create, update, delete, and inspect cron job runs
  • ap configView config versions, diff, drift check, and rollback

Productivity Commands

  • ap memoryView and manage agent memory entries
  • ap toolMonitor tool usage, status, and call history
  • ap reportGenerate, list, export, and schedule reports
  • ap templateBrowse, validate, and deploy verified templates
  • ap runbookList, trigger, inspect, and manage runbook executions
  • ap analyticsView usage analytics and performance metrics

System Commands

  • ap connectorManage connectors, discovery import, diagnostics, sync, and IM channels
  • ap runtime-hostList paired runtime hosts, discover instances, batch-add connectors, and sync attach-mode sessions
  • ap orgManage organizations, members, and roles
  • ap notificationView and manage notification preferences
  • ap health-checkRun system health checks and diagnostics
  • ap infrastructureView infrastructure status and service health
  • ap supply-chainView supply chain security and dependency intel

Utility Commands

  • ap authLogin, logout, refresh tokens, and check identity
  • ap profileManage stored connection profiles
  • ap exportExport data (agents, config, audit logs) as JSON/CSV
  • ap importImport configuration from file
  • ap routingView and manage A2A routing rules
  • ap capabilitiesDiscover agent capabilities and protocol support

Common Options#

These flags are available on most commands:

  • ---json — Output as JSON instead of formatted tables
  • ---page — Page number (default: 1)
  • ---page-size — Items per page (default: 20, max: 100)
  • ---date-from — Start date filter (YYYY-MM-DD)
  • ---date-to — End date filter (YYYY-MM-DD)
  • ---profile — Use a specific stored profile
  • ---confirm — Required for destructive operations (delete, logout)

Example Workflows#

Daily Monitoring

Quickly check the operator state with canonical dashboard, agent, and approval commands:

Terminal
$ ap dashboard summary
ap agent list --health-status error
ap approval list --status pending

Cost Investigation

Drill into cost changes with summary, by-agent, and trend commands:

Terminal
$ ap cost summary --date-from 2026-04-01
ap cost by-agent --date-from 2026-04-01
ap cost trend --granularity week --date-from 2026-04-01

Emergency Response

Inspect one agent, trigger the kill switch if needed, then inspect audit history:

Terminal
$ ap agent show <agent-id>
ap kill-switch trigger <agent-id> --reason "Unexpected outbound calls"
ap audit search --agent-id <agent-id> --date-from 2026-04-15

Runtime Host intake

Complete the paired-host discovery and session-sync loop from terminal only:

Terminal
$ ap runtime-host list
ap runtime-host discover <runtime-host-id>
ap runtime-host batch-add <runtime-host-id> --instance-key <instance-key>
ap runtime-host sync-sessions <runtime-host-id> --instance-key <instance-key>
CLI Reference — ClawButler User Manual