π 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
feat(plugins): ADR-098 Part 4 β standardize neural-learning hook
Reuven2e5c90c90289
diff --git a/plugins/ruflo-daa/agents/daa-specialist.md b/plugins/ruflo-daa/agents/daa-specialist.mdindex 4e3068e29a..662c537bb1 100644--- a/plugins/ruflo-daa/agents/daa-specialist.md+++ b/plugins/ruflo-daa/agents/daa-specialist.md@@ -33,3 +33,10 @@ npx @claude-flow/cli@latest memory search --query "cognitive pattern for TASK" -- **ruflo-intelligence**: SONA neural patterns power cognitive adaptation and trajectory learning- **ruflo-agentdb**: Pattern storage backend for DAA knowledge sharing++### Neural Learning++After completing tasks, feed the adaptive-agent learning loop:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-goals/agents/goal-planner.md b/plugins/ruflo-goals/agents/goal-planner.mdindex b4a236b302..5a17858d90 100644--- a/plugins/ruflo-goals/agents/goal-planner.md+++ b/plugins/ruflo-goals/agents/goal-planner.md@@ -80,3 +80,10 @@ Use MCP tools for persistence and learning:- `mcp__claude-flow__hooks_intelligence_trajectory-start` / `trajectory-step` / `trajectory-end` β record execution trajectories for learning- `mcp__claude-flow__neural_predict` β predict optimal approaches based on learned patterns- `mcp__claude-flow__workflow_create` / `workflow_execute` β codify repeatable plans as workflows++### Neural Learning++After completing a plan, feed the planner trajectory store so future replans inherit the outcome:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-intelligence/agents/intelligence-specialist.md b/plugins/ruflo-intelligence/agents/intelligence-specialist.mdindex bfabc63de0..ad7f4be378 100644--- a/plugins/ruflo-intelligence/agents/intelligence-specialist.md+++ b/plugins/ruflo-intelligence/agents/intelligence-specialist.md@@ -32,3 +32,10 @@ npx @claude-flow/cli@latest memory search --query "routing for TASK_TYPE" --name- **ruflo-agentdb**: HNSW-indexed pattern storage backing the intelligence pipeline's RETRIEVE step- **ruflo-daa**: Dynamic Agentic Architecture β cognitive patterns that feed into intelligence routing++### Neural Learning++After completing tasks, feed the pattern-discovery learning loop so the next RETRIEVE benefits from this run:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-iot-cognitum/agents/telemetry-analyzer.md b/plugins/ruflo-iot-cognitum/agents/telemetry-analyzer.mdindex 6d8a61d93d..027c3becb4 100644--- a/plugins/ruflo-iot-cognitum/agents/telemetry-analyzer.md+++ b/plugins/ruflo-iot-cognitum/agents/telemetry-analyzer.md@@ -44,3 +44,10 @@ Telemetry and anomalies are persisted to AgentDB with vector indexing:- **Readings**: `iot-telemetry` namespace, tagged by device and fleet- **Anomalies**: `iot-telemetry-anomalies` namespace, tagged by type and action- **Vector search**: HNSW-indexed similarity search across telemetry vectors (M=16, efConstruction=200)++### Neural Learning++After each analysis pass, feed the telemetry baseline learning so future Z-score thresholds adapt:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-ruvllm/agents/llm-specialist.md b/plugins/ruflo-ruvllm/agents/llm-specialist.mdindex 885fcacee9..f20a64dca1 100644--- a/plugins/ruflo-ruvllm/agents/llm-specialist.md+++ b/plugins/ruflo-ruvllm/agents/llm-specialist.md@@ -28,3 +28,10 @@ Store successful model configurations and prompt templates:npx @claude-flow/cli@latest memory store --namespace llm-configs --key "config-PROVIDER-MODEL" --value "PARAMS_AND_RESULTS"npx @claude-flow/cli@latest memory search --query "config for PROVIDER" --namespace llm-configs```++### Neural Learning++After each routing or fine-tune cycle, feed the router outcome learning so future provider/model picks compound this run:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-sparc/agents/sparc-orchestrator.md b/plugins/ruflo-sparc/agents/sparc-orchestrator.mdindex 084838d9f3..cb3b8a90dc 100644--- a/plugins/ruflo-sparc/agents/sparc-orchestrator.md+++ b/plugins/ruflo-sparc/agents/sparc-orchestrator.md@@ -136,3 +136,10 @@ Use learned patterns to predict phase durations and common blockers:- `mcp__claude-flow__hooks_intelligence_trajectory-start` / `trajectory-step` / `trajectory-end` β record execution trajectories- `mcp__claude-flow__neural_predict` / `neural_train` β predict and learn from SPARC cycles- `mcp__claude-flow__workflow_create` / `workflow_execute` β automate repeatable phase workflows++### Neural Learning++After each phase or full SPARC cycle, feed the phase-quality learning loop so quality gates self-tune:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```diff --git a/plugins/ruflo-swarm/agents/coordinator.md b/plugins/ruflo-swarm/agents/coordinator.mdindex 0713575796..7ebce514e5 100644--- a/plugins/ruflo-swarm/agents/coordinator.md+++ b/plugins/ruflo-swarm/agents/coordinator.md@@ -22,3 +22,10 @@ Anti-drift rules:- **ruflo-goals**: GOAP planning for complex multi-session objectives that swarms execute- **ruflo-autopilot**: Autonomous /loop execution of swarm-coordinated work++### Neural Learning++After completing a swarm cycle, feed the coordination outcome learning so topology + role choices compound:+```bash+npx @claude-flow/cli@latest hooks post-task --task-id "TASK_ID" --success true --train-neural true+```