migration-engineering

migration-engineering is a skill for Claude Code, Codex from magnus919/agent-skills. It costs 83 tokens per session (2,486 once invoked), scanned A, original, MIT.

A method for moving data, schemas, APIs, infrastructure, or services from one system to another while the old system may still be in use. It treats the transition as a staged change with compatibility, checking, cutover, and recovery.

In plain words
What is it for?
Use it to plan dual-running, reconciliation, API deprecation, schema changes, service extraction, infrastructure moves, and rollback or recovery.
Why use it?
It reduces the risk of broken readers, lost data, downtime, or an unsafe switch during a system migration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan dual-running, reconciliation, API deprecation, schema changes, service extraction, infrastructure moves, and rollback or recovery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magnus919/agent-skills/migration-engineering
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.

Any agent
npx skills add magnus919/agent-skills --skill migration-engineering
Clone the repo
git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin migration-engineering/plugin install migration-engineering after adding the marketplace above.

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-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/magnus919/agent-skills/migration-engineering/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/migration-engineering)
Your own site
<a href="https://agentmods.dev/skills/magnus919/agent-skills/migration-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/migration-engineering/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.

agentmods 80×15 button for migration-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/magnus919/agent-skills/migration-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/migration-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00083 $0.02486
Opus 5 $0.00042 $0.01243
Sonnet 5 $0.00017 $0.00497
Haiku 4.5 $0.00008 $0.00249

Measured 9d ago against content hash 6cbc9cda44a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

migration-engineering 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 9d 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.

migration-engineering/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migration Engineering

Plan and execute safe migrations across system boundaries. A migration is any change that moves data, schemas, interfaces, infrastructure, or services from a current state to a target state while preserving correctness, availability, and recoverability during the transition.

This skill owns the cross-system migration method — compatibility design, staging, reconciliation, cutover, recovery, and deprecation. It does not own the implementation details of any single technology or subsystem; those belong to specialist skills.

When to use

Load this skill when the task involves:

Trigger Example
A schema change that must not break existing readers or writers "Add a non-nullable column to a high-traffic table with zero downtime"
A data migration between stores or representations "Migrate user profiles from Postgres to a dedicated service with its own database"
An API version migration with a deprecation window "Move consumers from v1 REST to v2 GraphQL over six months"
An infrastructure or service migration "Shift a workload from self-hosted VMs to a managed platform across regions"
A cross-system change requiring dual-running and reconciliation "Replace the legacy billing engine with a new one while keeping both in sync"
Planning cutover, rollback, or irreversible steps for a migration "Define the recovery strategy for the warehouse schema migration"

When not to use

  • Single-technology quick fixes — if the change is confined to one system with no compatibility window, no dual-running, and no cross-system coordination, use the relevant specialist skill directly (e.g., data-engineering for a simple DDL change, api-design-and-evolution for a single-endpoint deprecation).
  • Tool-specific how-to guides — this skill provides the method, not vendor-specific instructions. It does not prescribe one migration technology, one database engine, one API gateway, or one infrastructure platform.
  • Migrations without a system boundary — in-place refactors, code rewrites that don't cross a data or interface boundary, or single-service configuration changes are not migration-engineering scope.
  • Guaranteeing rollback — this skill does not claim rollback is always possible. Some migrations include steps that are irreversible; the method requires identifying those steps explicitly and planning acceptance, communication, and contingency rather than implying a false safety net.

Read the full file on GitHub · 197 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. 9d ago First seen · 197 lines · 83 tokens per session scan A 6cbc9cda44a5

Subscribe to this mod's changes

migration-engineering is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,486 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 2026-09-03.