Pilot Swarm Task Farm Setup

Deploy a self-organizing compute swarm with 5 agents. Use this skill when: 1. User wants to set up a distributed task farm or compute swarm 2. User is config...

Security Scan

The skill's instructions, required binaries, and actions are coherent with a swarm setup; nothing requested is disproportionate to the stated purpose, though there are operational security considerations (trust handshakes, Slack bridge, installed skills) you should review before running.

Purpose & Capability

Name/description match what the SKILL.md does: it builds a 5-node swarm using pilotctl and clawhub to install related pilot-* skills and create a manifest. The declared required binaries (pilotctl, clawhub) are exactly the tools the instructions call.

Instruction Scope

Instructions stay within swarm setup scope (install skills with clawhub, set hostnames, write manifest, perform handshakes, publish/subscribe). Two points to note: (1) the monitor role installs 'pilot-slack-bridge' but the SKILL.md does not document how Slack credentials will be provided or secured; (2) handshake steps state 'trust is auto-approved' — that is a functional detail that grants network/trust relationships and should be done only between hosts you control.

Install Mechanism

This is an instruction-only skill (no install spec, no code files). Installation actions are performed via clawhub (a package/skill manager) and pilotctl which is consistent with the described workflow. No arbitrary URL downloads or archive extraction are present in this skill itself.

Credentials

The skill declares no required environment variables, which matches the instructions. However it asks you to install other skills (e.g., pilot-slack-bridge) that will likely need external credentials (Slack webhook/token). Those credential requirements are not surfaced here and should be expected to be requested by the installed skills themselves.

Persistence & Privilege

always is false and the skill does not request persistent system-wide privileges. It writes a manifest to ~/.pilot/setups/swarm-task-farm.json and installs other skills via clawhub — expected behavior for a setup skill and within its stated scope.

Assessment

This skill appears internally consistent for deploying a small Pilot swarm, but review these before running: - Verify you trust the sources and binaries (pilotctl, clawhub) and know where clawhub installs packages from, since it will install multiple pilot-* skills. - Expect additional credentials: the monitor's pilot-slack-bridge likely requires Slack tokens/webhooks; prepare and secure those separately. - Handshakes auto-approve trust. Only run handshake commands between hosts you control; unintended handshakes can grant other agents access to publish/subscribe on your swarm. - Confirm firewall/network rules for port 1002 and limit exposure to trusted networks. - Backup any existing ~/.pilot configs before writing the manifest, and review the contents of the installed pilot-* skills (especially pilot-formation and pilot-slack-bridge) if you need higher assurance.

Swarm Task Farm Setup

Deploy 5 agents: 1 leader, 3 workers, and 1 monitor.

Roles

Role	Hostname	Skills	Purpose
leader	<prefix>-leader	pilot-leader-election, pilot-formation, pilot-task-router, pilot-broadcast	Elected leader, distributes tasks
worker-N	<prefix>-worker-N	pilot-swarm-join, pilot-map-reduce, pilot-task-retry, pilot-metrics	Executes tasks, retries on failure
monitor	<prefix>-monitor	pilot-task-monitor, pilot-mesh-status, pilot-slack-bridge, pilot-metrics	Tracks swarm health

Setup Procedure

Step 1: Ask the user which role and prefix. For workers, also ask the worker number (1, 2, or 3).

Step 2: Install skills:

# leader:
clawhub install pilot-leader-election pilot-formation pilot-task-router pilot-broadcast
# worker (repeat for each):
clawhub install pilot-swarm-join pilot-map-reduce pilot-task-retry pilot-metrics
# monitor:
clawhub install pilot-task-monitor pilot-mesh-status pilot-slack-bridge pilot-metrics

Step 3: Set hostname and write manifest to ~/.pilot/setups/swarm-task-farm.json.

Step 4: Handshake — workers trust leader + monitor; leader trusts all workers + monitor.

Manifest Templates Per Role

leader

{
  "setup": "swarm-task-farm", "role": "leader", "role_name": "Swarm Leader",
  "hostname": "<prefix>-leader",
  "skills": {
    "pilot-leader-election": "Participate in leader election via consensus.",
    "pilot-formation": "Manage swarm membership.",
    "pilot-task-router": "Partition and distribute tasks to workers.",
    "pilot-broadcast": "Broadcast work units to all workers."
  },
  "data_flows": [
    { "direction": "send", "peer": "<prefix>-worker-1", "port": 1002, "topic": "task-assignment", "description": "Work units" },
    { "direction": "send", "peer": "<prefix>-worker-2", "port": 1002, "topic": "task-assignment", "description": "Work units" },
    { "direction": "send", "peer": "<prefix>-worker-3", "port": 1002, "topic": "task-assignment", "description": "Work units" },
    { "direction": "receive", "peer": "<prefix>-worker-1", "port": 1002, "topic": "task-result", "description": "Completed results" },
    { "direction": "receive", "peer": "<prefix>-worker-2", "port": 1002, "topic": "task-result", "description": "Completed results" },
    { "direction": "receive", "peer": "<prefix>-worker-3", "port": 1002, "topic": "task-result", "description": "Completed results" }
  ],
  "handshakes_needed": ["<prefix>-worker-1", "<prefix>-worker-2", "<prefix>-worker-3", "<prefix>-monitor"]
}

worker-N

{
  "setup": "swarm-task-farm", "role": "worker-N", "role_name": "Compute Worker",
  "hostname": "<prefix>-worker-N",
  "skills": {
    "pilot-swarm-join": "Join the swarm and register with leader.",
    "pilot-map-reduce": "Execute map-reduce work units.",
    "pilot-task-retry": "Retry failed tasks with exponential backoff.",
    "pilot-metrics": "Report CPU, memory, task throughput to monitor."
  },
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-leader", "port": 1002, "topic": "task-assignment", "description": "Work units" },
    { "direction": "send", "peer": "<prefix>-leader", "port": 1002, "topic": "task-result", "description": "Completed results" },
    { "direction": "send", "peer": "<prefix>-monitor", "port": 1002, "topic": "worker-metrics", "description": "Health metrics" }
  ],
  "handshakes_needed": ["<prefix>-leader", "<prefix>-monitor"]
}

monitor

{
  "setup": "swarm-task-farm", "role": "monitor", "role_name": "Swarm Monitor",
  "hostname": "<prefix>-monitor",
  "skills": {
    "pilot-task-monitor": "Track task completion rates and queue depth.",
    "pilot-mesh-status": "Monitor worker connectivity and latency.",
    "pilot-slack-bridge": "Alert on worker failures or stalled tasks.",
    "pilot-metrics": "Aggregate and display swarm metrics."
  },
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-worker-1", "port": 1002, "topic": "worker-metrics", "description": "Worker health" },
    { "direction": "receive", "peer": "<prefix>-worker-2", "port": 1002, "topic": "worker-metrics", "description": "Worker health" },
    { "direction": "receive", "peer": "<prefix>-worker-3", "port": 1002, "topic": "worker-metrics", "description": "Worker health" }
  ],
  "handshakes_needed": ["<prefix>-leader", "<prefix>-worker-1", "<prefix>-worker-2", "<prefix>-worker-3"]
}

Data Flows

• leader → worker-* : task assignments (port 1002)
• worker-* → leader : completed results (port 1002)
• worker-* → monitor : health metrics (port 1002)

Workflow Example

# On leader — distribute:
pilotctl --json publish <prefix>-worker-1 task-assignment '{"task_id":"T-001","type":"image_resize","input":"batch-a.zip"}'
# On worker-1 — complete:
pilotctl --json publish <prefix>-leader task-result '{"task_id":"T-001","status":"success","duration_s":34}'
pilotctl --json publish <prefix>-monitor worker-metrics '{"worker":"worker-1","cpu":72,"tasks_done":15}'

Dependencies

Requires pilot-protocol skill, pilotctl binary, clawhub binary, and a running daemon.