Composite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit record stored in the `metaharness-audit` memory…
Per-message cost breakdown within a single session. The drill-down companion to cost-anomaly — when an outlier session is flagged, this surfaces the specific expensive messages so…
Forward-looking spend extrapolation. Computes a USD-per-day rate from the recent measurement window, projects to 7d/30d/90d/365d horizons, and surfaces "days until budget…
Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)
Test-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass without modifying it.
Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation
Run `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy),…
Composite CI gate — runs cost-budget-check + cost-burn + cost-anomaly + cost-projection in parallel and surfaces a single combined health status with max exit code.
Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime
Run a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally
Enterprise-review-grade threat model from `harness threat-model <path>`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings.
5-dimension harness readiness scorecard from `metaharness score <path>`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd +…
Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics,…
Snapshot delta between two cost-summary JSON outputs. PR-level cost regression detection — answers "what changed between these two specific snapshots?".
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
One-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh…
Spawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed deep delegation
Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on…
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed.
Regulator-grade feature attribution for any LSTM/Transformer signal — single-entry PageRank ranks the top-K features that drove the prediction (ADR-126 Phase 6, ADR-123…
Multi-baseline counterfactual cost analysis. Compares actual session spend to hypothetical always-haiku / always-sonnet / always-opus routing baselines.
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness.
Burn-rate trend over time with optional drift-alert exit code. Bins session spend into buckets, surfaces window-over-window delta, and can exit 1 when latest bucket exceeds prior…
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch.
Manage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify <suite.json>` checks suite well-formedness.
MAD-based outlier detection on session spend. Robust to the very outliers it hunts (unlike mean+sigma).
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
Query AgentDB with semantic routing, hierarchical recall, causal graphs, and context synthesis
Pre/post task lifecycle hooks for quality gates, trajectory recording, and automated follow-through. Wraps every GFV operation with validation, logging, and pattern learning.
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration.
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying.
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination — from ruvnet/ruflo
Multi-source data truth resolution using Byzantine fault tolerance and weighted consensus. Reconciles conflicting data across HubSpot, ServiceTitan, GA4, and Google Ads.
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination — from ruvnet/ruflo
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management.
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination — from ruvnet/ruflo
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Add descriptions for new models from the HuggingFace router to chat-ui configuration. Use when new models are released on the router and need descriptions added to prod.yaml and…
Queen-led multi-agent orchestrator for GetFresh Ventures Growth by Design CEO AI Kit. Manages hierarchical agent dispatch, strategic/tactical/adaptive modes, royal directives, and…
Query the witness-anchored ruLake cache — search, verify, explain, or refresh. Returns ranked results plus a decision_trace block with cost, latency, witness match, and substrates…
Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server.
Event-driven workflow automation in Flow Nexus cloud. Use for creating, executing, and managing complex automated workflows with message queue processing and intelligent agent…
AI swarm orchestration and management in Flow Nexus cloud. Use for deploying, coordinating, and scaling multi-agent swarms for complex task execution.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations.
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern rec — from…
Neural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural network lifecycle management.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, and hybrid search for distributed AI systems.
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
Train RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPipe + ESP32 CSI → 92.9% PCK@20, ADR-079), RuVector contrastive…
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration.
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations.
5-phase structured planning methodology: Specification, Pseudocode, Architecture, Refinement, Completion. Enhances GFV planning mode with formalized phases and quality gates.