fire-migrate-database

A guided assistant for moving data between PostgreSQL, MySQL, SQLite, and SQL Server. A database is the system that stores an application’s structured data.

In plain words
What is it for?
Use it to assess, plan, execute, and verify migrations such as MySQL to PostgreSQL or SQLite to PostgreSQL, including plan-only assessments.
Why use it?
It turns a risky database change into an audited plan with explicit confirmation, while avoiding destructive actions without approval.

Command

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 commands/thierryn/fire-flow/fire-migrate-database
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,392 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 $0.00032 $0.04392
Opus 5 $0.00016 $0.02196
Sonnet 5 $0.00006 $0.00878
Haiku 4.5 $0.00003 $0.00439

Measured 2d ago against content hash 733e21f3c86e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-migrate-database 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 2d 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.

commands/fire-migrate-database.md · 550 lines

How it starts

The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-migrate-database — Database Migration Assistant

Guided migration between PostgreSQL, MySQL, SQLite, and SQL Server — powered by battle-tested dialect translation skills.

Purpose

Take a database migration from "I need to switch databases" to "migration verified and complete" through a structured 6-step pipeline. Uses the Dominion Flow database-solutions skills library as its knowledge base.

What this command does NOT do:

  • It does NOT touch your source database (read-only unless you explicitly approve a backup dump)
  • It does NOT execute destructive operations without confirmation
  • It does NOT guess — it audits first, then proposes

Arguments

Argument Required Default Description
direction No auto-detect Migration path: pg-to-mysql, mysql-to-pg, sqlite-to-pg, pg-to-sqlite, auto
source No Interactive Connection string, SQLite file path, or project directory to analyze
target No Interactive Target connection string, or plan-only for assessment without execution

Usage

# Fully interactive (guided wizard)
/fire-migrate-database

# Specify direction
/fire-migrate-database mysql-to-pg

# Full specification
/fire-migrate-database --direction mysql-to-pg --source "mysql://user:***@localhost/mydb" --target "postgresql://user:***@localhost/mydb_pg"
# NOTE: Read credentials from .env files, never pass them as command arguments.

# Assessment only — no execution
/fire-migrate-database --direction sqlite-to-pg --source ./mydb.sqlite --target plan-only

# Auto-detect from project code
/fire-migrate-database --source C:/Projects/my-app

Process

Step 1: Determine Migration Context

+---------------------------------------------------------------+
|          DATABASE MIGRATION ASSISTANT                           |
+---------------------------------------------------------------+
|                                                                 |
|  This wizard will guide you through a database migration.      |
|                                                                 |
|  Pipeline:                                                     |
|    1. DETECT   — Identify source and target databases          |
|    2. AUDIT    — Analyze schema, find breaking changes         |
|    3. PLAN     — Generate migration plan with translations     |
|    4. PREPARE  — Create migration scripts and app code patches |
|    5. EXECUTE  — Run the migration (with your approval)        |
|    6. VERIFY   — Validate data integrity and completeness      |
|                                                                 |
|  Safety: Source database is READ-ONLY throughout.              |
|                                                                 |
+---------------------------------------------------------------+

Read the full file on GitHub · 550 lines

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. 2d ago First seen · 550 lines · 32 tokens per session scan A 733e21f3c86e

Subscribe to this mod's changes

fire-migrate-database is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 32 tokens to every session and 4,392 once invoked, about $0.0002 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.