Customer Health Review with Claude Code: Sandbox Policy
A production playbook for customer health review in cross-industry operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: Customer success leaders
The problem
Customer success leaders need customer health review to run repeatedly against usage exports, support history, renewal notes, and account plans. 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 customer health 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 customer health 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