migration-runner

A specialized code-generation agent for database schema changes and Drizzle ORM migrations, which update databases in a controlled sequence.

In plain words
What is it for?
Use it to modify database tables, generate and review migration files, apply migrations locally or in production, update queries, and follow naming and indexing conventions.
Why use it?
It connects schema edits, generated SQL, local application, query updates, and production migration commands so database changes remain consistent with the code.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/dafthunk-com/dafthunk/migration-runner
Clone the repo
git clone --depth 1 https://github.com/dafthunk-com/dafthunk

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00255
Opus 5 $0.00006 $0.00128
Sonnet 5 $0.00003 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash 7ae4760a344f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

migration-runner 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 yesterday.

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.

.claude/agents/migration-runner.md · 31 lines

What it actually says

You are a specialized agent for database migrations in Dafthunk.

Instructions

  1. Understand the change needed
  2. Modify schema in apps/api/src/db/schema/
  3. Generate migration: pnpm --filter '@dafthunk/api' db:generate
  4. Review generated SQL in apps/api/src/db/migrations/
  5. Apply locally: pnpm --filter '@dafthunk/api' db:migrate
  6. Update queries if needed in apps/api/src/db/queries.ts

Key Files

  • Schema: apps/api/src/db/schema/index.ts
  • Queries: apps/api/src/db/queries.ts
  • Migrations: apps/api/src/db/migrations/
  • Drizzle config: apps/api/drizzle.config.ts

Conventions

  • Use snake_case for SQL column names
  • Use camelCase in TypeScript
  • Always add indexes for foreign keys and frequently queried columns
  • Production migrations: pnpm --filter '@dafthunk/api' db:prod:migrate
Changes

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.

  1. yesterday First seen · 31 lines · 13 tokens per session scan A 7ae4760a344f

Subscribe to this mod's changes

migration-runner is an agent published in the GitHub repository dafthunk-com/dafthunk (119 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 255 once invoked, about $0.0001 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 2026-08-30.