🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUvdb6469ce0671
diff --git a/.claude/agents/dual-mode/codex-coordinator.yaml b/.claude/agents/dual-mode/codex-coordinator.yamlnew file mode 100644index 0000000000..ffbe3a2e79--- /dev/null+++ b/.claude/agents/dual-mode/codex-coordinator.yaml@@ -0,0 +1,150 @@+name: codex-coordinator+description: Coordinates multiple headless Codex workers for parallel execution+type: coordinator+platform: dual++# Execution mode+execution:+ mode: interactive+ spawns_workers: true+ worker_type: codex-worker++# Capabilities+capabilities:+ - swarm-coordination+ - task-decomposition+ - result-aggregation+ - worker-management++# MCP Integration+mcp:+ enabled: true+ tools:+ - swarm_init+ - swarm_status+ - agent_spawn+ - memory_search+ - memory_store+ - memory_list+ - hive-mind_init+ - hive-mind_spawn++# Coordination patterns+patterns:+ parallel_workers:+ description: Spawn multiple workers for parallel execution+ steps:+ - swarm_init: { topology: hierarchical, maxAgents: 8 }+ - spawn_workers:+ - { type: coder, count: 2 }+ - { type: tester, count: 1 }+ - { type: reviewer, count: 1 }+ - wait_for_completion+ - aggregate_results++ sequential_pipeline:+ description: Chain workers in sequence+ steps:+ - spawn: architect+ - wait_for: architecture+ - spawn: [coder-1, coder-2]+ - wait_for: implementation+ - spawn: tester+ - wait_for: tests+ - aggregate_results++# Prompts+prompts:+ coordinate_parallel: |+ You are the coordinator for a parallel Codex swarm.++ TASK: {{task_description}}++ STEP 1: Initialize swarm+ ```bash+ npx claude-flow swarm init --topology hierarchical --max-agents {{worker_count}}+ ```++ STEP 2: Spawn headless workers+ {{#each workers}}+ ```bash+ claude -p "{{this.prompt}}" --session-id {{this.id}} &+ ```+ {{/each}}++ STEP 3: Wait for completion+ ```bash+ wait+ ```++ STEP 4: Aggregate results+ ```bash+ npx claude-flow memory list --namespace results+ ```++ spawn_worker: |+ Spawning worker: {{worker_name}}+ Task: {{worker_task}}+ Session: {{session_id}}++ ```bash+ claude -p "+ You are {{worker_name}}.++ TASK: {{worker_task}}++ 1. Search memory: memory_search(query='{{task_keywords}}')+ 2. Execute your task+ 3. Store results: memory_store(key='result-{{session_id}}', namespace='results', upsert=true)+ " --session-id {{session_id}} &+ ```++# Worker templates+workers:+ coder:+ prompt_template: |+ You are a coder worker.+ Implement: {{task}}+ Path: {{output_path}}+ Store results when complete.++ tester:+ prompt_template: |+ You are a tester worker.+ Write tests for: {{task}}+ Path: {{test_path}}+ Run tests and store results.++ reviewer:+ prompt_template: |+ You are a code reviewer.+ Review: {{files}}+ Check for: security, performance, best practices+ Store findings in memory.++ documenter:+ prompt_template: |+ You are a documentation writer.+ Document: {{component}}+ Output: {{doc_path}}+ Store completion status.++# Examples+examples:+ - name: Feature implementation swarm+ description: Coordinate 4 workers for feature implementation+ script: |+ #!/bin/bash+ FEATURE="user-auth"++ # Initialize+ npx claude-flow swarm init --topology hierarchical --max-agents 4++ # Spawn workers+ claude -p "Architect: Design $FEATURE" --session-id ${FEATURE}-arch &+ claude -p "Coder: Implement $FEATURE" --session-id ${FEATURE}-code &+ claude -p "Tester: Test $FEATURE" --session-id ${FEATURE}-test &+ claude -p "Docs: Document $FEATURE" --session-id ${FEATURE}-docs &++ wait+ npx claude-flow memory list --namespace results