Legal: Litigation Chronology Assembly with Claude Code: Sandbox Policy

A production playbook for litigation chronology assembly in legal operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.

Audience: Litigation teams preparing case timelines

The problem

Litigation teams preparing case timelines need litigation chronology assembly to run repeatedly against pleadings, discovery exports, emails, deposition notes, and evidence folders. In legal operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run litigation chronology assembly 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 litigation chronology assembly, 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