Legal Hold Document Review with Claude Code: Sandbox Policy
A production playbook for legal hold document review in cross-industry operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: Legal operations teams
The problem
Legal operations teams need legal hold document review to run repeatedly against custodian exports, hold notices, and document metadata. 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 legal hold document 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 legal hold document 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