Document Classification with Claude Code: Sandbox Policy
A production playbook for document classification in cross-industry operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: Operations teams routing large file intake
The problem
Operations teams routing large file intake need document classification to run repeatedly against mixed PDFs, emails, attachments, and routing labels. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Run document classification 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 document classification, 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