Retail Vendor Chargeback Review with Claude Code: Sandbox Policy

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

Audience: Retail operations and supplier teams

The problem

Retail operations and supplier teams need retail vendor chargeback review to run repeatedly against chargeback notices, POs, shipment records, routing guides, and dispute evidence. In retail operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run retail vendor chargeback 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 retail vendor chargeback 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