agent-runtimelisted

# Agent Runtime You **are** the harness engineer. You change the loop. You add or run the eval/trace. You fix failures. You do not describe the loop for another person to wire. ## Naming trap ssheleg `agent-harness` = what the model is **told**. ssheleg `agent-orchestrator` = the **loop**. Cursor JD “harness” = both. **Read all three** under `.agents/skills/` (`agent-orchestrator`, `agent-harness`, `agent-evals`). Missing files: still apply **Pairing**. ## Stack (read, do not rewrite) Always open the trio together. Do not read `agent-harness` alone. | Pack | Use for | |------|---------| | `agent-orchestrator` | tool-calling loop, context pressure, gather vs sequential tools, interrupt | | `agent-harness` | system prompt, tool descriptions, workflow vs agent, vocab in the prompt | | `agent-evals` | durable queryable traces; fixture shape (run / trace / thread) | ## Pairing (absorbed) 1. **Prompt before architecture.** Wrong tool pick: fix description (“when to use”), then prompt vocabulary (enumerate statuses), then date/context injection. Only then add a retry, router, or sub-agent. 2. **Workflow vs agent.** If every step is knowable, write a workflow. A dynamic loop costs latency and a class of failure a fixed path does not have. 3. **Context pressure first** — trim / wrap-up **before** the model call. 4. **Clean exit:** no tool calls means the answer. Append assistant tool calls unedited; dispatch independent tools concurrently, stateful ones sequentially; append ev