Retail: Product Catalog Cleanup with Claude Code: Sandbox Policy
A production playbook for product catalog cleanup in retail operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: Retail and marketplace catalog teams
The problem
Retail and marketplace catalog teams need product catalog cleanup to run repeatedly against product feeds, images, descriptions, taxonomy rules, and exception lists. In retail operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Run product catalog cleanup 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 product catalog cleanup, 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