Localization Review with Claude Code: Sandbox Policy

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

Audience: Localization and product teams

The problem

Localization and product teams need localization review to run repeatedly against strings, screenshots, glossaries, and market 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

Run localization 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 localization 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