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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sigistry/marketplace/migration-safety)<a href="https://agentmods.dev/commands/sigistry/marketplace/migration-safety"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/migration-safety/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sigistry/marketplace/migration-safety"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/migration-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.01049 |
| Opus 5 | $0.00010 | $0.00524 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
migration-safety 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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze the migration in $ARGUMENTS (or the migration files in the current diff if no path is given) for operations that take blocking table locks, rewrite the hazardous steps into a safe expand-contract sequence, and produce a paired rollback. This is a static analysis, no database connection is used. Load the safe-migrations skill for the lock catalog and expand-contract recipes.
Process
Step 1: Detect dialect and framework
Read the target file. Determine the dialect (Postgres vs MySQL/InnoDB, infer from types like serial/jsonb/text vs AUTO_INCREMENT/ENGINE=InnoDB, or from config). Determine the framework by file path and syntax:
| Framework | Signal |
|---|---|
| Raw SQL | .sql, V1__*.sql, *.up.sql/*.down.sql |
| Alembic | alembic/versions/, def upgrade()/downgrade(), op. |
| Django | migrations/, class Migration, operations = [...] |
| Rails/ActiveRecord | db/migrate/, class ... < ActiveRecord::Migration, change/up/down |
| Prisma | prisma/migrations/, migration.sql |
| Flyway | V<n>__*.sql, U<n>__*.sql |
| Liquibase | changelog, <changeSet> XML/YAML |
| Knex / TypeORM / Sequelize / golang-migrate | exports.up, queryRunner., queryInterface., *.up.sql |
Step 2: Classify every DDL operation by lock
For each operation, look it up in the safe-migrations skill references (postgres-locks.md, mysql-locks.md). Flag the hazardous ones:
| Hazard | Lock taken | Why it hurts |
|---|---|---|
ADD COLUMN ... NOT NULL DEFAULT <volatile> |
ACCESS EXCLUSIVE + full rewrite |
Blocks all reads/writes while every row is rewritten |
ALTER COLUMN ... TYPE |
ACCESS EXCLUSIVE + rewrite |
Full-table rewrite under exclusive lock |
ADD CONSTRAINT NOT NULL / CHECK (validated) |
ACCESS EXCLUSIVE + full scan |
Blocks writes during validation |
CREATE INDEX (non-CONCURRENTLY) |
SHARE (blocks writes) |
Writes queued for the whole build |
ADD FOREIGN KEY (validated) |
SHARE ROW EXCLUSIVE on both tables |
Blocks writes, scans child table |
| Column rename / drop in one deploy | ACCESS EXCLUSIVE + breaks running app code |
Old deploy still references old name |
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.
- 5d ago First seen · 60 lines · 19 tokens per session scan A 9822b51a9509
migration-safety is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,049 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 2026-09-03.
Other commands, from other repositories
f5-db
Database operations and migrations.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
compliance-fix
Show Qualimetry review findings for a file and apply the standards-compliant fix.
refactor-stack
Coordinated architecture refactor — change database, cloud provider, or framework with full SDL consistency.
f5-jira
Jira integration - setup, sync, status, convert, issues, attachments.