squads version.
squads init
Plant the seed: create manager agent, CLI skill, and starter squads| Option | Description |
|---|---|
-p, --provider <provider> | LLM provider (claude, gemini, openai, ollama, none) |
--pack <packs...> | Additional squad packs to install (engineering, marketing, operations, all) |
--skip-infra | Skip infrastructure setup prompt |
--force | Skip requirement checks (for CI/testing) |
-y, --yes | Accept all defaults (non-interactive mode) |
-q, --quick | Quick init - create files only, skip interactive prompts |
squads add
Add a new squad with directory structure and starter files| Option | Description |
|---|---|
-d, --description <text> | Squad mission (one sentence) |
-g, --goal <text> | First goal for the squad |
-m, --model <model> | Default model (default: sonnet) |
-f, --force | Overwrite existing squad |
-y, --yes | Accept all defaults (non-interactive) |
-r, --repo | Create a GitHub repository for the squad |
-o, --org <org> | GitHub organization for —repo (default: detected from git remote) |
squads run
Run a squad or agent (no target lists squads). Use —org to run all squads as one coordinated cycle.| Option | Description |
|---|---|
-v, --verbose | Verbose output |
-d, --dry-run | Show what would be run without executing |
-a, --agent <agent> | Run specific agent within squad |
-t, --timeout <minutes> | Per-agent execution timeout in minutes (default: 15) |
-p, --parallel | Run all agents in parallel (N tmux sessions) |
-l, --lead | Lead mode: single orchestrator using Task tool for parallelization |
-b, --background | Run agent in background (detached process) |
-w, --watch | Run in background but tail the log for visibility |
--use-api | Use API credits instead of subscription |
--effort <level> | Effort level: high, medium, low (default: from SQUAD.md or high) |
--skills <skills...> | Skills to load (skill IDs or local paths) |
--provider <provider> | LLM provider: anthropic, google, openai, mistral, xai, aider, ollama |
--model <model> | Model to use (e.g., opus, sonnet, haiku, gemini-2.5-flash, gpt-4o) |
--trigger <type> | Trigger source: manual, scheduled, event, smart (default: manual) |
--cloud | Dispatch execution to cloud worker via API (requires squads login) |
--task <directive> | Founder directive for conversation mode (replaces lead briefing) |
--max-turns <n> | Max conversation turns (default: 20) (default: 20) |
--cost-ceiling <usd> | Cost ceiling in USD (default: 25) (default: 25) |
--no-verify | Skip post-execution verification (Ralph loop) |
--execute | Explicitly execute agents (default for run <target>) |
-j, --json | Output as JSON |
-i, --interval <minutes> | Autopilot: minutes between cycles (default: 30) |
--max-parallel <count> | Autopilot: max parallel squad loops (default: 2) |
--budget <usd> | Autopilot: daily budget cap ($) (default: 0) |
--once | Autopilot: run one cycle then exit |
--phased | Autopilot: use dependency-based phase ordering (from SQUAD.md depends_on) |
--no-eval | Skip post-run COO evaluation |
--org | Run all squads as a coordinated org cycle (scan → plan → execute → report) |
--force | Force re-run squads that already completed today |
--resume | Resume org cycle from where quota stopped it |
-y, --yes | Skip the org-run cost confirmation (for deliberate/non-interactive triggers) |
--focus <mode> | Cycle focus: create, resolve, review, ship, research, cost (default: create) |
squads list
List squads (alias for: squads status)squads orchestrate
Run squad with lead agent orchestration| Option | Description |
|---|---|
-f, --foreground | Run lead in foreground (interactive) |
-v, --verbose | Show detailed output and watch events |
-t, --timeout <minutes> | Maximum runtime in minutes (default: 60) |
squads env
View squad execution environment (MCP, skills, model, budget)squads env show
Show execution environment for a squad| Option | Description |
|---|---|
--json | Output as JSON |
squads env prompt
Output ready-to-use prompt for Claude Code execution| Option | Description |
|---|---|
-a, --agent <agent> | Agent to execute (required) |
--json | Output as JSON |
squads exec
View execution history and statisticssquads exec list
List recent executions| Option | Description |
|---|---|
-s, --squad <squad> | Filter by squad |
-a, --agent <agent> | Filter by agent |
--status <status> | Filter by status (running, completed, failed) |
-n, --limit <n> | Number of executions to show (default: 20) |
--json | Output as JSON |
squads exec show
Show execution details| Option | Description |
|---|---|
--json | Output as JSON |
squads exec stats
Show execution statistics| Option | Description |
|---|---|
-s, --squad <squad> | Filter by squad |
--json | Output as JSON |
squads log
Show run history with timestamps, duration, and status| Option | Description |
|---|---|
-s, --squad <squad> | Filter by squad |
-a, --agent <agent> | Filter by agent |
-n, --limit <n> | Number of runs to show (default: 20) (default: 20) |
--since <date> | Show runs since date (e.g. 7d, 2026-04-01) |
-j, --json | Output as JSON |
squads dashboard
Show dashboards. Use “squads dash” for overview, “squads dash <name>” for specific dashboard, “squads dash —list” to see all.squads dash
| Option | Description |
|---|---|
-v, --verbose | Show additional details |
-c, --ceo | Executive summary with priorities and blockers |
-f, --full | Include GitHub PR/issue stats (slower, ~30s) |
-l, --list | List available declarative dashboards |
--view <view> | Render specific view from dashboard |
-j, --json | Output as JSON |
squads status
Show squad status and state| Option | Description |
|---|---|
-v, --verbose | Show detailed status |
-j, --json | Output as JSON |
squads context
Get business context for alignment: goals, memory, costs, activitysquads feed
| Option | Description |
|---|---|
-s, --squad <squad> | Focus on specific squad |
-t, --topic <topic> | Search memory for relevant context |
-a, --agent | Output JSON for agent consumption |
-j, --json | Output as JSON (alias for —agent) |
-v, --verbose | Show additional details |
squads cost
Show cost summary (today, week, by squad)| Option | Description |
|---|---|
-s, --squad <squad> | Filter to specific squad |
--json | Output as JSON |
squads budget
Check budget status for a squad| Option | Description |
|---|---|
--json | Output as JSON |
squads usage
Show local cost/token usage (today, rolling window, by squad)| Option | Description |
|---|---|
-w, --window <hours> | Rolling-window size in hours (default: 5) |
--json | Output as JSON |
squads health
Quick health check for all infrastructure services| Option | Description |
|---|---|
-v, --verbose | Show optional services |
squads doctor
Check local tools, auth, and project readiness| Option | Description |
|---|---|
-v, --verbose | Show install hints and optional tools |
squads history
Show recent agent execution history| Option | Description |
|---|---|
-d, --days <days> | Days to look back (default: 7) |
-s, --squad <squad> | Filter by squad |
-v, --verbose | Show cost and token details |
-j, --json | Output as JSON |
squads results
Show squad results: git activity + KPI goals vs actuals| Option | Description |
|---|---|
-d, --days <days> | Days to look back (default: 7) |
-v, --verbose | Show detailed KPIs per goal |
squads goal
Manage squad goalssquads goal set
Set a goal for a squad| Option | Description |
|---|---|
-m, --metric <metrics...> | Metrics to track |
squads goal list
List goals for squad(s)| Option | Description |
|---|---|
-a, --all | Show completed goals too |
-j, --json | Output as JSON |
squads goal complete
Mark a goal as completedsquads goal progress
Update goal progresssquads kpi
Track and analyze squad KPIs (defined in SQUAD.md frontmatter)squads kpi list
List all KPIs across squads| Option | Description |
|---|---|
-j, --json | Output as JSON |
squads kpi show
Show KPI status for a squad| Option | Description |
|---|---|
-j, --json | Output as JSON |
squads kpi record
Record a KPI value| Option | Description |
|---|---|
-n, --note <note> | Add a note to the record |
-j, --json | Output as JSON |
squads kpi trend
Show KPI trend over time| Option | Description |
|---|---|
-p, --periods <n> | Number of periods to show (default: 7) |
-j, --json | Output as JSON |
squads kpi insights
Generate insights from KPI data| Option | Description |
|---|---|
-j, --json | Output as JSON |
squads progress
Track active and completed agent tasks| Option | Description |
|---|---|
-v, --verbose | Show more activity |
squads progress start
Register a new active tasksquads progress complete
Mark a task as completed| Option | Description |
|---|---|
-f, --failed | Mark as failed instead |
squads feedback
Record and view execution feedbacksquads feedback add
Add feedback for last execution (rating 1-5)| Option | Description |
|---|---|
-l, --learning <learnings...> | Learnings to extract |
squads feedback show
Show feedback history| Option | Description |
|---|---|
-n, --limit <n> | Number of entries to show (default: 5) |
squads feedback stats
Show feedback summary across all squadssquads autonomy
Show autonomy score and confidence metrics| Option | Description |
|---|---|
-s, --squad <squad> | Filter by squad |
-p, --period <period> | Time period: today, week, month (default: today) |
-j, --json | Output as JSON |
squads autopilot
[deprecated] Use “squads run” instead — autopilot mode when no target givensquads daemon
| Option | Description |
|---|---|
-i, --interval <minutes> | Minutes between cycles (default: 30) |
-p, --parallel <count> | Max parallel agent runs (default: 2) |
-b, --budget <dollars> | Max daily spend in dollars (0 = unlimited/subscription) (default: 0) |
--once | Run one cycle and exit |
--dry-run | Show what would run without dispatching |
-v, --verbose | Show detailed scoring |
squads stats
Show agent outcome scorecards: merge rate, waste, cost per outcome| Option | Description |
|---|---|
-p, --period <period> | Time period: 7d or 30d (default: 7d) |
-j, --json | Output as JSON |
squads memory
Query and manage squad memorysquads memory query
Search across all squad memory| Option | Description |
|---|---|
-s, --squad <squad> | Limit search to specific squad |
-a, --agent <agent> | Limit search to specific agent |
squads memory read
Show memory for a squadsquads memory write
Add to squad memory| Option | Description |
|---|---|
-a, --agent <agent> | Specific agent (default: squad-lead) |
-t, --type <type> | Memory type: state, learnings, feedback (default: learnings) |
squads memory list
List all memory entriessquads memory sync
Sync memory from git: pull remote changes, process commits, optionally push to Postgres| Option | Description |
|---|---|
-v, --verbose | Show detailed commit info |
-p, --push | Push local memory changes to remote after sync |
--no-pull | Skip pulling from remote |
--postgres | Sync cycle data (goals, feedback, KPIs, learnings) to Postgres |
--dimensions | Sync squad/agent definitions to Postgres dim tables |
--learnings | Sync learnings.md files to Postgres |
--auto-learn | Auto-generate learnings from session commits |
squads memory search
Search stored conversations (requires authentication: squads login)| Option | Description |
|---|---|
-l, --limit <limit> | Number of results (default: 10) |
-r, --role <role> | Filter by role: user, assistant, thinking |
-i, --importance <importance> | Filter by importance: low, normal, high |
squads memory extract
Extract memories from recent conversations into Engram| Option | Description |
|---|---|
-s, --session <session> | Extract specific session only |
-h, --hours <hours> | Look back period in hours (default: 24) |
-d, --dry-run | Preview without sending to Engram |
squads learn
Capture a learning for future sessions| Option | Description |
|---|---|
-s, --squad <squad> | Squad to associate learning with |
-c, --category <category> | Category: success, failure, pattern, tip |
-t, --tags <tags> | Comma-separated tags |
--context <context> | Additional context |
squads learnings
View and search learningssquads learnings show
Show learnings for a squad| Option | Description |
|---|---|
-n, --limit <n> | Number to show (default: 10) |
-c, --category <category> | Filter by category |
--tag <tag> | Filter by tag |
squads learnings search
Search learnings across all squads| Option | Description |
|---|---|
-n, --limit <n> | Max results (default: 10) |
squads sync
Git memory synchronization (Postgres sync optional)| Option | Description |
|---|---|
-v, --verbose | Show detailed commit info |
-p, --push | Push local memory changes to remote after sync |
--no-pull | Skip pulling from remote |
--postgres | Sync cycle data to Postgres |
squads trigger
Manage smart triggerssquads trigger list
List triggerssquads trigger sync
Sync SQUAD.md triggers to schedulersquads trigger fire
Manually fire a triggersquads trigger enable
Enable a triggersquads trigger disable
Disable a triggersquads trigger status
Show scheduler statussquads approval
Manage approval requests for agent actionssquads approval send
Send approval request to Slack| Option | Description |
|---|---|
-t, --title <title> | Approval title |
-d, --description <desc> | Detailed description |
-s, --squad <squad> | Squad name |
-a, --agent <agent> | Agent name |
-p, --priority <n> | Priority 1-10 (1=urgent) (default: 5) |
-e, --expires-in <time> | Expiration time (24h, 1h, 30m) (default: 24h) |
-j, --json <json> | Full payload as JSON (use - for stdin) |
squads approval list
List approvals| Option | Description |
|---|---|
--pending | Only show pending approvals (default: true) |
-s, --squad <squad> | Filter by squad |
-j, --json | Output as JSON |
squads approval check
Check approval status| Option | Description |
|---|---|
-w, --wait | Wait for decision (polls every 5s) |
-t, --timeout <minutes> | Wait timeout in minutes (default: 60) |
squads approval cancel
Cancel pending approvalsquads autonomous
Local scheduling daemon for autonomous agent executionsquads auto
squads autonomous start
Start the scheduling daemonsquads autonomous stop
Stop the scheduling daemonsquads autonomous status
Show daemon status, running agents, and next runssquads autonomous pause
Pause the daemon (e.g. quota exhausted)squads autonomous resume
Resume a paused daemonsquads sessions
Show active Claude Code sessions across squads| Option | Description |
|---|---|
-v, --verbose | Show session details |
-j, --json | Output as JSON |
squads sessions history
Show session history and statistics| Option | Description |
|---|---|
-d, --days <days> | Days of history to show (default: 7) |
-s, --squad <squad> | Filter by squad |
-j, --json | Output as JSON |
squads sessions summary
Show pretty session summary (auto-detects current session or pass JSON)| Option | Description |
|---|---|
-d, --data <json> | JSON data for summary (overrides auto-detection) |
-f, --file <path> | Path to JSON file with summary data |
-j, --json | Output as JSON instead of pretty format |
squads session
Manage current session lifecyclesquads session start
Register a new session| Option | Description |
|---|---|
-s, --squad <squad> | Override squad detection |
-q, --quiet | Suppress output |
squads session stop
End current session| Option | Description |
|---|---|
-q, --quiet | Suppress output |
squads session heartbeat
Update session heartbeat| Option | Description |
|---|---|
-q, --quiet | Suppress output |
squads detect-squad
Detect current squad based on cwd (for use in hooks)squads login
Log in to Squads (Pro & Enterprise)squads logout
Log out from Squadssquads whoami
Show current logged in usersquads eval
Evaluate agent readiness for deployment (e.g., squads eval company/coo)| Option | Description |
|---|---|
-j, --json | Output as JSON |
-v, --verbose | Show detailed scoring info |
squads deploy
Deploy agents to the Squads platform| Option | Description |
|---|---|
-n, --dry-run | Show what would be deployed without pushing |
-s, --squad <squad> | Deploy only a specific squad |
-v, --verbose | Show detailed agent and trigger info |
squads deploy status
Show current platform deployment statussquads deploy pull
Pull execution data and learnings from platform| Option | Description |
|---|---|
-v, --verbose | Show detailed execution info |
squads cognition
Business cognition engine — beliefs, decisions, reflectionssquads cognition brief
Executive summary: hot beliefs + recent signals + pending decisionssquads cognition beliefs
Display world model beliefs| Option | Description |
|---|---|
-d, --domain <domain> | Filter by domain (revenue/product/operations/market/team) |
-j, --json | Output as JSON |
squads cognition decisions
Decision journal with outcome scores| Option | Description |
|---|---|
-e, --evaluated | Only show evaluated decisions |
-j, --json | Output as JSON |
squads cognition reflect
Trigger meta-cognition reflection| Option | Description |
|---|---|
-s, --scope <scope> | Reflection scope (business, squad:X, agent:X) (default: business) |
squads contract
Agent Contracts — the governed definition of what each agent may dosquads contract validate
Derive + validate every agent contract; non-zero exit on any violation| Option | Description |
|---|---|
--squad <name> | validate a single squad |
--json | machine-readable output |
squads catalog
Service catalog — browse, inspect, and validate servicessquads catalog list
List all services in the catalog| Option | Description |
|---|---|
--type <type> | Filter by type (product, domain) |
--json | Output as JSON |
squads catalog show
Show detailed info for a service| Option | Description |
|---|---|
--json | Output as JSON |
squads catalog check
Run scorecard checks for a service (or all)| Option | Description |
|---|---|
--json | Output as JSON |
squads release
Release management — pre-deploy checks and statussquads release pre-check
Validate dependencies and health before deploying a service| Option | Description |
|---|---|
--skip-health | Skip health endpoint checks |
squads obs
Observability — execution history, token costs, and trendssquads obs history
Show execution history with tokens and cost| Option | Description |
|---|---|
-s, --squad <squad> | Filter by squad |
-a, --agent <agent> | Filter by agent |
-n, --limit <n> | Number of records (default: 20) |
--since <date> | Since date (ISO or relative: 1d, 7d, 30d) |
--json | Output as JSON |
squads obs cost
Show token spend summary| Option | Description |
|---|---|
-p, --period <period> | Time period: today, 7d, 30d, all (default: 7d) |
--json | Output as JSON |
squads obs sync
Backfill JSONL execution data to Postgres (Tier 2)| Option | Description |
|---|---|
--dry-run | Show what would be synced without sending |
squads tier
Show active infrastructure tier and available services| Option | Description |
|---|---|
--json | Output as JSON |
squads services
Manage local Docker services for your projectsquads services up
Start local services (Docker required)| Option | Description |
|---|---|
--file <path> | Path to docker-compose.yml |
squads services down
Stop local services| Option | Description |
|---|---|
--file <path> | Path to docker-compose.yml |
squads services status
Show running Docker containers and health| Option | Description |
|---|---|
--file <path> | Path to docker-compose.yml |
squads goals
Dashboard of all squad goals — status at a glance| Option | Description |
|---|---|
-s, --squad <squad> | Show goals for a specific squad |
--json | Output as JSON |
squads credentials
Manage per-squad GCP service accounts and credentialssquads credentials create
Create a service account and key for a squad| Option | Description |
|---|---|
--force | Recreate even if credential exists |
squads credentials create-all
Create credentials for all squads with GCP config in SQUAD.md| Option | Description |
|---|---|
--force | Recreate even if credentials exist |
squads credentials rotate
Rotate a squad credential (create new key, delete old)squads credentials list
List all squad credentials and their statussquads credentials revoke
Delete a squad service account and all keyssquads review
Post-cycle evaluation — goals, costs, blockers, founder actions| Option | Description |
|---|---|
-s, --squad <squad> | Detail view for a specific squad |
--since <period> | Look back period (e.g. 24h, 7d, 30d) (default: 7d) |
--json | Output as JSON |
squads brief
Read recent sessions, extract founder intentions, create GitHub issues| Option | Description |
|---|---|
-n, --sessions <n> | Number of recent sessions to read (default: 5) |
--dry-run | Show proposed issues without creating them |
--coo | Write founder-focus.md for COO context |
squads providers
Show available LLM CLI providers (claude, gemini, codex, etc.)| Option | Description |
|---|---|
-j, --json | Output as JSON |
squads update
Check for and install updates| Option | Description |
|---|---|
-y, --yes | Auto-confirm update without prompting |
-c, --check | Check for updates without installing |
squads version
Show version informationsquads commands
List the live command tree (machine-readable with —json)| Option | Description |
|---|---|
--json | Output as JSON |
--all | Include hidden/removed commands |