Results for “meta-harness”

Harness Compound

Design domain-specific agent teams, define specialized agents, and generate the skills they use. Use when you need to decompose a complex project into coordinated multi-agent teams, choose the right architecture pattern (pipeline, fan-out/fan-in, expert pool, producer-reviewer, supervisor, hierarchical delegation), generate .claude/agents/ and .claude/skills/ files, or validate and iterate on generated harnesses. Triggers on: harness, build a harness, design agent team, agent team architecture, multi-agent skill generation, set up harness, harness engineering, domain agent team, harness for this project.

Make any software agent-native with HKUDS CLI-Anything — four routed modes: install ready-made harnesses via CLI-Hub (cli-hub list/search/info/install/launch), give agents the cli-hub-meta-skill for autonomous discovery, generate a new harness from any codebase/repo via the 7-phase /cli-anything pipeline, or iterate with :refine/:test/:validate; 40+ harnesses, 2,461 tests, Click CLIs with REPL + --json.

Prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.

Harness Strategy

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting. Combines Monte Carlo scenario analysis, calibrated confidence, multi-perspective debate, and optimal path planning. Use before any complex decision, build, or task. Activates on: 'deep confidence', 'think before you act', 'plan first', 'Atlas mode', 'reason through this', 'what should I do', 'think this through', 'best approach', 'reason carefully', 'plan and execute'.

CQO quality and operational governance lead. Owns gates, regression strategy, memory hygiene, port/service policy, and archive approval.

HR hiring. Searches .harness/shared/HR-Resource candidates, installs selected worker skills into .claude and .codex, and records roster wiring.

Designs autonomous agent harnesses with locked evaluators, editable surfaces, durable logging, novelty gates, pruning, rollback, and human approval boundaries.

Harness Pulse

ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term memory, modular skills (research/report/slides). Built on LangChain + LangGraph. Triggers on: 'deerflow', 'deer-flow', 'bytedance agent', 'super agent harness', 'LangGraph agent orchestration', 'multi-hour agent tasks', 'spawn sub-agents', 'agent sandbox docker', 'persistent agent memory', 'agent skills system', 'AI research orchestrator', 'long-running agent tasks', 'agent with memory', 'langgraph orchestrator', 'IM channel agent integration'.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

CEO/Dispatcher. Owner-facing mission intake, CXX meeting orchestration, event routing, and final Owner reports. Trigger with /goal, /submission, /hot-fix, /ceo.

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

Use when adding a new agent harness (CLI-based coding agent) adapter to adapters. Covers capability audit, adapter scaffold, session parsing, auth detection, hooks/plugins wiring, tests, and docs.

COO planning lead. Hires planners, researchers, hypothesis developers, documentation workers, technical writers, visual storytellers, and narratologists to turn a goal into evidence-backed product direction and user-facing communication (user guides, explanation videos, onboarding content, how-we-built-it storytelling).

Meta-Analysis Master with Data Integrity, Effect Size, Error Prevention & Sensitivity Multi-gate validation and workflow orchestration for meta-analysis. Absorbed C6 (Data Integrity Guard), C7 (Error Prevention Engine), B3 (Effect Size Extractor), E5 (Sensitivity Analysis - Meta) capabilities Triggers: meta-analysis, pooled effect, heterogeneity, forest plot, funnel plot, Hedges g, data integrity, effect size extraction, sensitivity analysis

Orchestrating specialist AI agent teams as a meta-coordinator: decomposes requests into minimum viable chains, spawns each as an independent session, drives to final output. For multi-domain tasks.

Harness E2E

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Implements Manifold-Constrained Hyper-Connections (mHC) using Doubly Stochastic Matrices to improve deep learning stability.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new problems.

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B.

Bidirectional conversion between Haskell and Roc. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Haskell↔Roc specific patterns. Use when migrating Haskell applications to Roc's platform model, translating lazy pure functional code to strict platform-based architecture, or refactoring type class based designs to ability-based patterns. Extends meta-convert-dev with Haskell-to-Roc specific patterns.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and platform-specific Kubernetes work for EKS, GKE, AKS, OpenShift, GitOps controllers, or observability stacks.

Inspect and manipulate transformer internals via HookPoints and activation caching for mechanistic interpretability research.

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Conduct passive OSINT reconnaissance on target organizations using a MITRE ATT&CK framework. Discovers employees, email patterns, subdomains, infrastructure, leaked credentials, and cloud assets with confidence-scored findings.

Searches and loads runnable skill guidance from two skill corpora via MCP or CLI, with admin commands for feedback, outcomes, and reindexing.

Simulates man-in-the-middle attacks using Ettercap, mitmproxy, and Bettercap in authorized environments to intercept, analyze, and modify network traffic for testing encryption enforcement, certificate validation, and detection capabilities.

Applies medicinal-chemistry filters with the medchem library — drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, and molecular complexity metrics for compound prioritization and library cleanup. Use when filtering or triaging a compound library, flagging PAINS or reactive groups, or assessing drug-likeness of candidate molecules. Part of the AlterLab Academic Skills suite.