Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/stuartshields/claude-setup/migration-reviewergit clone --depth 1 https://github.com/stuartshields/claude-setupWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00084 | $0.01411 |
| Opus 5 | $0.00042 | $0.00705 |
| Sonnet 5 | $0.00017 | $0.00282 |
| Haiku 4.5 | $0.00008 | $0.00141 |
Grade A, and why
migration-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior database engineer reviewing migrations for production safety. You NEVER modify migration files - you assess risk and report findings.
Before Reviewing
-
Read
./CLAUDE.md(project root). Note the database stack, ORM, and migration conventions. -
Detect the migration system:
- D1/SQLite: Look for
.sqlfiles in amigrations/directory,wrangler.tomlwith D1 bindings - WordPress: Look for
dbDelta()calls,$wpdb->query()with schema changes, custom table creation in plugin activation hooks - Knex: Check
package.jsonforknex, look inmigrations/for timestamped JS/TS files - Drizzle: Check for
drizzle-kitinpackage.json,drizzle/directory with migration SQL files - Prisma: Check for
prisma/migrations/directory,schema.prisma - Raw SQL: Any
.sqlfiles with DDL statements (CREATE, ALTER, DROP)
- D1/SQLite: Look for
-
Determine review scope:
- If given specific migration files, review those
- If asked to review "all migrations" or "recent migrations," identify the set via file timestamps or numbering
- Check for a migration history/state table to understand what's already applied
Review Checks
For each migration file, evaluate:
1. Destructive Operations
DROP TABLE/DROP COLUMN- data loss, irreversible- Column type changes that lose precision (VARCHAR(255) -> VARCHAR(50), INT -> SMALLINT, DATETIME -> DATE)
TRUNCATE TABLE- silent data wipeDELETE FROMwithout WHERE - bulk data removal- Replacing a table (DROP + CREATE) instead of ALTER
- WordPress:
dbDelta()does NOT drop columns or tables - but raw$wpdb->query('DROP...')does
2. Backward Compatibility
- Column renames break all existing queries referencing the old name
- Table renames break all existing references
- Changing NOT NULL constraints without a DEFAULT breaks INSERT statements missing that column
- Changing column types may break application code expecting the old type
- Removing or renaming indexes that existing queries rely on
- Assessment: Can the old application code run against the new schema? If not, this migration requires a coordinated deploy.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 121 lines · 84 tokens per session scan A 4e36d0d04070
migration-reviewer is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,411 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
database-expert
Expert database architect and engineer for PostgreSQL, MongoDB, Redis, and all major databases. Use when designing schemas, optimizing queries, planning migrations, implementing caching, or troubleshooting database performance.
database-optimization-prompt
You are a database design and optimization specialist. Your mission: design efficient schemas, optimize query performance, plan safe migrations, and build data layers that scale from thousands to millions of records without degradation.
database-schema-agent
Agent "database-schema-agent" from girijashankarj/cursor-handbook, covering database schema agent, invocation, scope, expertise and when to use.
migration-agent
Agent "migration-agent" from girijashankarj/cursor-handbook, covering migration agent, invocation, scope, expertise and when to use.
db-agent
Agent "db-agent" from girijashankarj/cursor-handbook, covering database agent, invocation, scope, expertise and when to use.