Last commit on April 1, 2026·Created on April 1, 2026
keli-wen/agentic-harness-patterns-skill
“Maps the harness that separates a demo agent from a production system.”
Combined rank
#508
across all skills
Stars
301
7d change unavailable
Forks
49
Watchers
3
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This skill collection documents the architectural patterns that live outside the LLM call loop: memory persistence, lazy-loaded skills, fail-closed permission pipelines, context budgeting, and multi-agent coordination. It gives AI agent runtime engineers, platform teams, and multi-agent system architects a structured reference for the non-obvious design decisions — concurrency classification per call, all-or-nothing hook trust, two-phase memory saves — that determine whether an agent scales reliably.
WHO IT'S FOR
AI Agent Runtime Engineers
building production agent harnesses
Platform / DevEx Teams
designing agent infrastructure for developers
Tool Safety / Permission Engineers
implementing fail-closed tool permission pipelines
Multi-agent System Architects
designing coordinator, fork, and swarm delegation patterns
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Compatibility not documented
Want to install it?
NPX Skills AddRepository instructions