checklists, monitors and subagents: the essential current harness architecture
Subagents, checklists and monitors are the three building blocks that turn a bare inference-loop coding harness into a modern one.
3 pieces tagged coding agents.

Subagents, checklists and monitors are the three building blocks that turn a bare inference-loop coding harness into a modern one.

Subagents in the same session used to feel like overkill. Opus 5.5 changes that — so I put together the parts I love from Claude, Codex and pi-subagents.

sessions running for months, contexts bloated with hundreds of skills and sessions plauged with compactions - the sorry state of affairs in the workbench of ai-natives