n-agentic-harnesses-codex

name	n-agentic-harnesses-codex
description	Designs, evaluates, and improves agentic harnesses for developer tools, assistants, workflow runtimes, copilots, and AI-powered products. Applies when work involves defining or reviewing tool-use architecture, permissions, workflow state, durability, context and memory systems, evaluation strategy, observability, user experience, or phased implementation plans for an agentic system.
metadata	{"priority":6,"pathPatterns":["**/*harness*","**/*agent-runtime*","**/*agent_runtime*","**/*orchestrat*","**/*workflow*","**/*tool-registry*","**/*tool_registry*","**/*permission*","**/*approval*","**/*state-machine*","**/*state_machine*","**/*session*","**/*memory*","**/*eval*","**/*retry*"],"importPatterns":["@modelcontextprotocol/*","langgraph","@langchain/*","langchain","@vercel/workflow"],"bashPatterns":["\\bnpm\\s+(install|i|add)\\s+[^\\n]*(langgraph|langchain|@vercel/workflow|@modelcontextprotocol)\\b","\\bpnpm\\s+(install|i|add)\\s+[^\\n]*(langgraph|langchain|@vercel/workflow|@modelcontextprotocol)\\b","\\bbun\\s+(install|i|add)\\s+[^\\n]*(langgraph|langchain|@vercel/workflow|@modelcontextprotocol)\\b","\\byarn\\s+add\\s+[^\\n]*(langgraph|langchain|@vercel/workflow|@modelcontextprotocol)\\b"],"promptSignals":{"phrases":["agentic harness","agent harness","ai harness","harness architecture","agent architecture","agent runtime","agent workflow runtime","tool-use architecture","tool use architecture","tool calling system","tool registry","capability registry","permission layer","approval gate","human-in-the-loop","workflow state","session persistence","durable agent","durable workflow","resume after crash","crash-safe agent","retry and idempotency","context assembly","memory system","evaluation harness","replay evals","agent observability","operator visibility","multi-agent architecture","single agent vs multi-agent","stop reasons"],"allOf":["[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]","[Truncated]"],"anyOf":["agent orchestration","approval workflow","tool-calling runtime","tool calling runtime","state machine","retry policy"],"noneOf":[],"minScore":6}}

N Agentic Harnesses For Codex

Use this skill as a router for designing, building, and evaluating agentic harnesses.

Read only the files you need. Do not load the entire reference set unless the request genuinely spans multiple subsystems.

Default posture:

• Bias toward lean, solo-maintainable architecture.
• Start with a single-agent design unless clear constraints justify more.
• Require an evaluation plan even for greenfield builds.
• Prefer explicit system boundaries, permission policy, and workflow state over prompt cleverness.
• Translate ideas into implementation phases, success criteria, and failure tests.

Step 1: Classify The Request

Choose one mode before reading reference files.

design

Use when the user is creating a new harness, planning a major rebuild, or asking for architecture, MVP, or implementation sequencing.

Default reads:

• references/01-principles-and-solo-dev-defaults.md
• references/02-harness-shapes-and-architecture.md
• references/08-design-and-build-playbook.md

Add subsystem files only as needed.

evaluation

Use when the user already has a harness and wants gaps, risks, missing primitives, UX upgrades, or architectural cleanup.

Default reads:

• references/01-principles-and-solo-dev-defaults.md
• references/09-evaluation-and-improvement-playbook.md

Add subsystem files only for the parts under review.

design + evaluation

Use when the user wants a target architecture and a way to verify it, compare it with an existing system, or define acceptance criteria before building.

Default reads:

• references/01-principles-and-solo-dev-defaults.md
• references/02-harness-shapes-and-architecture.md
• references/08-design-and-build-playbook.md
• references/09-evaluation-and-improvement-playbook.md

Step 2: Classify The Product Shape

Determine the closest product shape before going deeper:

• code agent
• chat assistant
• workflow orchestrator
• internal copilot
• embedded AI product feature
• hybrid system

If the request is ambiguous, pick the closest shape and state the assumption.