Data Room Indexing with Claude Code: Sandbox Policy

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

Audience: Deal teams and diligence operators

The problem

Deal teams and diligence operators need data room indexing to run repeatedly against folders of PDFs, spreadsheets, and evidence files. 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 data room indexing 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 data room indexing, 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