Agent Memory Audit with Claude Code: API Runtime Pattern
A production playbook for agent memory audit in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: AI platform and privacy teams
The problem
AI platform and privacy teams need agent memory audit to run repeatedly against stored memories, policies, logs, and deletion requests. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the agent memory audit instructions as a skill, send stored memories, policies, logs, and deletion requests as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For agent memory audit, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=agent-memory-audit
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo