This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
Install
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill harness-engineeringnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill harness-engineering -a claude-code -gnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill harness-engineering -a codex -ggemini skills install https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering.git --path skills/harness-engineeringgh skill install muratcankoylan/Agent-Skills-for-Context-Engineering harness-engineeringgit clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/harness-engineering ~/.claude/skills/harness-engineering # Claude Code
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/harness-engineering ~/.agents/skills/harness-engineering # Codex, Cursor, Gemini CLI, Copilot, OpenCode