agent-harness
Design, debug, or evaluate the runtime around a model-driven agent: loop, model adapter, tools, context, permissions, orchestration, extensibility, and verification. Use for Codex, Claude Code, DSH, Pi, Prime Agent, local-model integrations, or coding-agent harnesses; not for ordinary application code.
Pinned to revision 941659f4068d, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/agent-harness/SKILL.md
- skills/agent-harness/references/harness-matrix.md
- skills/agent-harness/references/incident-guards.md
- skills/agent-harness/references/lfm3-pi.md
Every link opens the file at its source, pinned to the revision this page describes.