Claude DB

The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-db:fix command) AFTER the user has confirmed the diffs. Applies AUTO/PROPOSED fixes, generates reversible timestamped migrations, backs up first, refuses a dirty git tree unless --force, is idempotent, and re-verifies each change.

Read-only migration-safety specialist. Use proactively during a database audit to analyze migration reversibility, lock level, table rewrites, destructive operations, enum mutation, and schema drift. Runs scripts/lint-migration.mjs. Feeds the Performance & Scale score.

Read-only NoSQL paradigm specialist. Use proactively during a database audit of document, key-value, or wide-column stores to analyze antipattern fit and access-pattern alignment — unbounded arrays, missing partition/sort keys, hot keys, fan-out, denormalization drift, and idempotency. Feeds both scores via the natural module's axis.

Read-only performance & scale specialist. Use proactively during a database audit to analyze indexing, index hygiene, query patterns, concurrency, connection pooling, partitioning/sharding, replicas/views, and storage/bloat. Feeds the Performance & Scale score.

Read-only schema & data-integrity specialist. Use proactively during a database audit to analyze normalization, primary-key strategy, referential integrity, types/precision, constraints, defaults/generated columns, naming, temporal/history, multitenancy, and security/access. Feeds the Design & Integrity score.

Audit a database schema, ORM model, or migrations for design and performance — produces two independent 0-100 scores (Design & Integrity + Performance & Scale) plus a prioritized, evidence-backed report. Read-only; never writes or migrates. Use when the user asks to audit, analyze, review, check, or score a database, schema, data model, migrations, indexes, keys, referential integrity, types, constraints, query patterns, partitioning, or connection pooling — for Postgres, MySQL, Mongo, DynamoDB, Cassandra, pgvector, ClickHouse, Neo4j, and friends.

Render a production-readiness GO/NO-GO grid for a database — runs a read-only audit, then maps the findings onto a fixed launch checklist (PITR/backups, RLS on tenant tables, FK indexes, money-as-numeric, timestamptz/UTC, connection pooling sized, migration reversibility, secrets-not-in-schema, charset/utf8mb4). Each row is PASS/WARN/FAIL/NEEDS-LIVE with the finding id, topped by a plain-language verdict. Read-only. Use when the user asks if a database is production-ready, ready to launch/ship, a go/no-go, a pre-launch or readiness checklist, or what to fix before going live.

Unified cross-paradigm anti-pattern catalog (M19) — relational and NoSQL smells that no single structural module owns cleanly: EAV / generic key-value tables, the "god table" with hundreds of columns, comma-separated lists in a column, polymorphic associations without FK, boolean-flag soup, Mongo unbounded array growth, deeply nested documents, the document fan-out / "join in app code" trap, Redis as a relied-on durable primary store. Each finding is re-homed to inherit the natural module's category. Feeds the Design & Integrity AND Performance & Scale scores depending on the smell.

Audit concurrency correctness — transaction isolation level, lost-update / read-modify-write races, queue-worker contention (SKIP LOCKED), and idempotency for key-value / document / wide-column writes. Module M14. Feeds the Performance & Scale score.

Audit connection management — serverless functions opening direct Postgres connections, transaction-mode pooler misuse (PgBouncer / Supabase / prepared statements), and pool sizing against backend max_connections. Module M15. Feeds the Performance & Scale score.

3 hooks across 1 event