nucleus_agents
Manage agent lifecycles, spawn specialized sub-agents, run automated code review and repair, orchestrate agent swarms, search persistent memory, and ingest tasks from external sources.
Instructions
Manage multi-agent lifecycles including spawning specialized sub-agents, running automated code review and repair, orchestrating agent swarms for complex tasks, searching persistent memory, ingesting tasks from external sources, and viewing real-time dashboards. Use this tool when you need to create new agents, review or fix code, coordinate parallel work, or query the knowledge base. Do NOT use for individual task CRUD (use nucleus_tasks), session management (use nucleus_sessions), or cross-brain sync (use nucleus_federation). Actions: 'spawn_agent' creates a sub-agent with a specific role (reviewer/implementer/researcher) and goal (side effect: may start a new process). 'critique_code' runs automated code review on a file, returning issues and suggestions. 'fix_code' attempts automated repair of a described issue in a file. 'apply_critique' applies review feedback. 'orchestrate_swarm' coordinates multiple agents working on a complex task in parallel. 'search_memory' queries the persistent engram store by keyword (read-only). 'read_memory' retrieves a specific engram by key. 'ingest_tasks' imports tasks from external sources like GitHub issues, CSV, or JSONL files (side effect: creates tasks). 'rollback_ingestion' undoes a previous import (destructive: deletes imported tasks). 'ingestion_stats' shows import history. 'dashboard' shows live system metrics including agent count, task throughput, and memory usage. 'snapshot_dashboard'/'list_dashboard_snapshots' manage dashboard snapshots. 'get_alerts'/'set_alert_threshold' configure monitoring alerts. 'respond_to_consent'/'list_pending_consents' handle human-in-the-loop approval flows for sensitive operations. Prerequisites: .brain directory. Returns JSON with {success: boolean, data: object}. Example: {action: 'search_memory', params: {query: 'authentication', limit: 5}} returns {success: true, data: {results: [{key: 'engram_x', content: 'Auth uses JWT...', score: 0.95}]}}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Select the agent management action. 'search_memory'/'read_memory'/'dashboard'/'get_alerts'/'ingestion_stats'/'list_pending_consents'/'session_briefing'/'list_dashboard_snapshots' are read-only. 'spawn_agent' creates a new sub-agent. 'critique_code'/'fix_code'/'apply_critique' handle automated code review and repair. 'orchestrate_swarm' coordinates parallel agents. 'ingest_tasks' imports from external sources. 'rollback_ingestion' is destructive (deletes imported tasks). 'set_alert_threshold' configures monitoring. 'respond_to_consent' approves/denies sensitive operations. | |
| params | No | Action-specific parameters as key-value pairs. spawn_agent: {role: string (required, 'reviewer'|'implementer'|'researcher'|'planner'), goal: string (required, what the agent should accomplish), tools: string[] (optional, tool names to grant access to)}. critique_code: {file_path: string (required, path to file to review), diff: string (optional, specific diff to focus review on)}. fix_code: {file_path: string (required), issue: string (required, description of the problem to fix)}. search_memory: {query: string (required, search term), limit: integer (optional, default 10)}. read_memory: {key: string (required, engram key)}. ingest_tasks: {source: string (required, 'github'|'csv'|'jsonl'), file_path: string (required, path to source file)}. set_alert_threshold: {metric: string (required, metric name), threshold: number (required), operator: string (optional, 'gt'|'lt'|'eq', default 'gt')}. handoff_task: {task_id: string (required), to_agent: string (required), context: object (optional)}. respond_to_consent: {consent_id: string (required), approved: boolean (required)}. rollback_ingestion/ingestion_stats/dashboard/snapshot_dashboard/list_dashboard_snapshots/get_alerts/list_pending_consents/session_briefing/register_session/apply_critique/orchestrate_swarm: no parameters needed. |