Database Migration Review with Claude Code: API Runtime Pattern
A production playbook for database migration review in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Backend teams shipping schema changes
The problem
Backend teams shipping schema changes need database migration review to run repeatedly against migration files, ORM models, production query samples, and rollback notes. 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 database migration review instructions as a skill, send migration files, ORM models, production query samples, and rollback notes 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 database migration review, 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=database-migration-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo