aktonay/skillz / skills/agent-harness/harness2
harness2
VerifiedHarness²: Recursive Agent Harnessing (Google Research / arXiv:2610.14224). Dynamically adapts and self-improves the agent execution harness on-the-fly using dual-level recursion (Propose-Probe-Compose and Harnessing Recursion).
Harness² — Recursive Agent Harnessing for Open-World Tasks
Based on Google Research (arXiv:2610.14224), Harness² enables recursive self-improvement (RSI) for LLM agents without retraining or updating underlying model weights. It operates by iteratively diagnosing, adapting, and evolving the execution harness (tools, prompts, memory, validators, and middleware).
Dual-Level Recursive Architecture
Level 1: Task-Level Recursion (Propose – Probe – Compose)
When facing an open-world task where ground-truth automated verifiers may not exist:
- Propose: Generate candidate repairs or modifications to the current harness and plan.
- Probe: Run lightweight diagnostic probes and contrastive execution traces to assess viability and side effects.
- Compose: Synthesize successful probe elements into an upgraded execution harness tailored to solve the immediate task.
Level 2: Harnessing-Level Recursion
- Extracts generalized insights across task-level runs.
- Updates the agent's long-term harness library without accumulating noise or catastrophic forgetting.
- Evaluates whether new harness patterns (guardrails, tool definitions, verification heuristics) improve performance on benchmark suites.
How to Apply Harness²
- Contrastive Trace Analysis: When an agent hits an execution error, contrast the failing run against previous successful patterns.
- Harness Mutation: Adjust prompt constraints, tool parameters, or verification gates dynamically.
- Probe Validation: Validate the mutation on a sandboxed sub-problem before committing to the full task.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |