| name | nate-b-jones-auto-improvement-loops |
| description | Designs, deploys, and safeguards self-improving agent systems using Nate B. Jones's adaptation of the Karpathy loop to business harnesses (not training code). Covers triplet definition, readiness audit, trace infrastructure, emergent affordances, safety governance, and the 5-layer prerequisite build (context → trace → eval → sandbox → governance). Use when building any auto-optimizing agent, evaluating organizational readiness for auto-improvement, auditing existing Phase 2 / evolution systems against frontier patterns, detecting metric gaming or silent degradation, or upgrading score-only logging to reasoning-trajectory logging. Trigger proactively whenever the user asks "how do I make this agent improve itself" or describes a Phase 2 evolution loop. For agent coordination use nate-b-jones-orchestration-intelligence; for memory/context optimization use nate-b-jones-context-engineering; for the underlying MetaHarness research methodology use self-evolving-systems. |
| expert | Nate B Jones |
| domain | AI/Automation — Self-Improving Agent Systems |
| version | 1 |
| source | "The Karpathy Loop — Auto-Research to Auto-Agent, Local Hard Takeoff in Business" (YouTube, April 2026) |
Nate B Jones — Auto-Improvement Loops
The magic isn't in the agent's intelligence — it's in the constraints. One editable file, one metric, one time budget. Build the foundations, or auto-improvement degrades your system faster than humans could.
Core Capability
Design, deploy, and safeguard self-improving agent systems using the Karpathy loop architecture. Distinguishes auto-research (optimizing model internals) from auto-agent (optimizing harness scaffolding — the universal pattern for every agent-deploying business). Covers the full lifecycle: triplet definition → readiness audit → meta/task architecture → trace infrastructure → emergent affordances → safety → deployment → system-level self-application.
What This Skill Produces
| Workflow | Output |
|---|
| Karpathy Triplet Design | Three-part specification (editable surface + metric + time budget) with fuzziness audit and gate decision |
| Auto-Improvement Readiness Audit | 5-layer prerequisite scorecard with gap remediation plan |
| Meta-Task Architecture Design | Full split architecture: meta-agent spec, task-agent spec, model-empathy constraint, handoff protocol |
| Trace Infrastructure Blueprint | Reasoning-trajectory logging schema, storage, analysis layer for any agent system |
| Emergent Behavior Playbook | Explicit harness affordances for 7 documented emergent patterns |
| 4-Mode Safety Audit | Detection + response mechanisms for gaming, drift, contamination, cascade |
| Local Hard Takeoff Deployment Plan | End-to-end rollout: system selection → infrastructure → first 3 cycles → promotion → scale |
| Phase 2 Karpathy Audit | META — applies this skill to Antigravity's Phase 2 system; prescribes concrete upgrades (advisory only) |
Workflow Table (by Tier)
Tier 1 — Foundation
| # | Workflow | Slash | When Deployed |
|---|
| 01 | Karpathy Triplet Design | /nate-auto-triplet | Before any auto-improvement project — the gate |
| 02 | Auto-Improvement Readiness Audit | /nate-auto-audit | Assessing whether team/system is ready |
