Agent Harness Engineering | Agent Skills Atlas

About this skill

Use when designing, building, refactoring, or recovering an LLM agent runtime/control harness, including its loop, provider capabilities, typed tools/state, context/memory, policy/isolation, budgets, cancellation, recovery, or delegation, even inside a coding or non-coding product request. Not for prompt-only work, generic app architecture, vendor CLI commands, evaluation-only work, or skill creation.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Unavailable

HTTP 404

About scan coverage and limitations

Original listing metadata

Original name

agent-harness-engineering

Original description

About this listing

Category: Engineering
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.