Construction: Change Order Audit with Claude Code: Sandbox Policy
A production playbook for change order audit in construction operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: Construction finance and project controls teams
The problem
Construction finance and project controls teams need change order audit to run repeatedly against change orders, contracts, invoices, schedules, and field reports. In construction operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Run change order audit in an ephemeral sandbox, keep provider credentials in the broker, expose narrow tools, and store logs outside the workspace for review.
Tradeoffs and failure modes
A narrower runtime blocks ambient machine behavior, but it gives security reviewers a concrete boundary. For change order audit, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Runtime boundary
filesystem: /skill and /skill/.argo/inputs only
network: deny by default
artifacts: /skill/output/artifacts
logs: retained outside sandbox
provider: Claude Code
Run this on Argo