agent-harness
Agent harness — what the agent is told, and how to audit what someone else told theirs
agent-orchestrator wires the loop. agent-evals proves it behaves. agent-interop gets
it talking to other processes. This skill is the layer between them and the model: the
prompt, the tools, and the choice of technique. Harness engineering includes
context management as well as instructions. Its effect depends on the task,
model and evaluation; benchmark gains do not establish a universal improvement.
It runs in both directions. Building one and auditing one are the same checklist read forwards and backwards, which is why they live together here.
Triggers
"tool description", "agent loops forever", "prompt engineering", "harness engineering", "ReAct loop", "react pattern", "static or dynamic", "embed an agent", "agent SDK", "Pi harness", "встроить агента".
Moved here from the description in 0.31.3: "agent picks the wrong tool", "агент не вызывает тул", "audit this agent".