migration-safety

migration-safety is a skill for Claude Code, Codex from evolplus/talos. It costs 55 tokens per session (622 once invoked), scanned A, original, Apache-2.0.

A pre-deployment review for changes to databases, schemas, queues, search indexes, or stored data. It checks how the change will run, what could go wrong, and whether it can be recovered.

In plain words
What is it for?
Use it to classify migrations, check backups and restore plans, review dry runs, estimate runtime impact, and define a safe execution order. It also records approvals, blockers, and risk levels.
Why use it?
It helps find data-loss risks, long locks, downtime, unsafe ordering, and rollback limits before a migration reaches users. A migration is a planned change to stored data or its structure.

Skill for Claude CodeCodex

Part of the talos plugin — 55 skills, 2 commands, 4 hooks shipped together

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 skills/evolplus/talos/migration-safety
Any agent
npx skills add evolplus/talos --skill migration-safety
Clone the repo
git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Or install talos, the plugin that ships this one along with the rest of its 55 skills, 2 commands, 4 hooks.

Wrote 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.

agentmods badge for migration-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/evolplus/talos/migration-safety.svg)](https://agentmods.dev/skills/evolplus/talos/migration-safety)
Your own site
<a href="https://agentmods.dev/skills/evolplus/talos/migration-safety"><img src="https://agentmods.dev/badge/skills/evolplus/talos/migration-safety.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 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 $0.00055 $0.00622
Opus 5 $0.00028 $0.00311
Sonnet 5 $0.00011 $0.00124
Haiku 4.5 $0.00006 $0.00062

Measured 3d ago against content hash 4c794e284698, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/migration-safety/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migration Safety

When to use

Use this skill whenever a deployment includes schema changes, data migrations, queue/topic changes, search index rebuilds, object-storage rewrites, or irreversible data operations.

Inputs and outputs

  • Inputs: migration files, ORM migration plan, architecture data contracts, affected services, target environment, backup policy, expected data volume, and rollback plan.
  • Outputs: migration safety verdict, execution order, preflight/dry-run evidence, backup/restore notes, risk classification, and blockers.

Procedure

  1. Classify the migration. Label as additive, backfill, destructive, contract/removal, reindex, data rewrite, or operational maintenance. Destructive/irreversible work needs explicit approval.
  2. Check compatibility. Prefer expand-contract: deploy additive schema first, release compatible code, backfill safely, then remove old fields in a later release.
  3. Estimate runtime impact. Identify locks, table scans, long transactions, index builds, queue replays, and service downtime. Require batching or online migration tools when needed.
  4. Verify backup and restore. Record backup location/status by name only, restore procedure, owner, and latest restore-test evidence. Do not read backup credentials.
  5. Run dry-run/preflight. Use local/staging with production-like schema where possible. For production, use native dry-run/explain tooling or a reviewed plan before mutation.
  6. Coordinate app versioning. Verify old and new app versions tolerate the migration during rolling deploy and rollback.
  7. Define failure handling. Record pause/resume, retry, rollback, manual repair, and "stop-the-line" thresholds.
  8. Emit verdict. safe, safe-with-conditions, or blocked.

Hard rules

  • Never run a migration against staging or production without an explicit target and approval.
  • Never approve destructive or irreversible migrations without backup/restore evidence and human sign-off.
  • Never assume rollback is possible after data deletion, type narrowing, irreversible transforms, or external side effects.
  • Never print database URLs, credentials, tokens, dumps, or row-level sensitive data.
  • Never couple schema removal with first code deployment unless architecture explicitly proves compatibility.

Read the full file on GitHub · 45 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. 3d ago First seen · 45 lines · 55 tokens per session scan A 4c794e284698

Subscribe to this mod's changes

migration-safety is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 29d ago), licensed Apache-2.0. It adds 55 tokens to every session and 622 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

moderator-page-migration

Port a moderator page from the main Next.js app (src/pages/moderator/) into apps/moderator. Use when asked to migrate, move or cut over a /moderator/ page to the spoke, or to port its tRPC procedures and Prisma services to SvelteKit loads/actions and Kysely.

civitai/civitai · 71 tokens

prisma-upgrade-v7

Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".

nitrocloudofficial/nitrostack · 67 tokens

ddia-systems

Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…

wondelai/skills · 138 tokens

sqlitecpp-update-sqlite

How to update the bundled SQLite3 amalgamation (sqlite3/sqlite3.c and sqlite3.h), the Meson wrap, README.md, and CHANGELOG.md. Use when upgrading SQLite, refreshing the vendored amalgamation, or bumping the sqlite3 wrap.

SRombauts/SQLiteCpp · 61 tokens

dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK…

awslabs/agent-plugins · 227 tokens