Construction: RFI And Submittal Review with Claude Code: Sandbox Policy

A production playbook for RFI and submittal review in construction operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.

Audience: Construction project teams

The problem

Construction project teams need RFI and submittal review to run repeatedly against RFIs, submittals, drawings, specs, change orders, and project notes. In construction operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run RFI and submittal review 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 RFI and submittal review, 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