Runbook Execution with Claude Code: Cost Controls
A production playbook for runbook execution in cross-industry operations using Claude Code: cost controls, run-scoped inputs, logs, typed results, and artifacts.
Audience: Operations teams automating repeatable SOPs
The problem
Operations teams automating repeatable SOPs need runbook execution to run repeatedly against runbooks, credentials policy, inputs, and escalation rules. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Set explicit limits for runbook execution: input size, run time, tool calls, artifacts, retries, and concurrent runs per organization.
Tradeoffs and failure modes
Limits reject pathological runs, but they keep one workflow from turning into an unbounded infrastructure bill. For runbook execution, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run limits
max_run_seconds=1800
max_input_bytes=104857600
max_artifact_bytes=104857600
max_tool_calls=120
retry_after_seconds=60
Run this on Argo