migrator

A specialist for moving a system from one schema, framework, runtime, API, or event format to another across multiple deployments. It uses expand, backfill, switch, and contract phases so each stage can be deployed and reversed.

In plain words
What is it for?
Use it for multi-deployment migrations that need staged changes, data backfills, dual support, rollback planning, and a final removal of the old version.
Why use it?
It reduces the risk of breaking a live system while code and data are changing at different times.

Agent

Part of the swe-workbench plugin — 1 skill, 24 commands, 32 agents, 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 agents/lugassawan/swe-workbench/migrator
Clone the repo
git clone --depth 1 https://github.com/lugassawan/swe-workbench

Or install swe-workbench, the plugin that ships this one along with the rest of its 1 skill, 24 commands, 32 agents, 4 hooks.

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,365 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 $0.00062 $0.02365
Opus 5 $0.00031 $0.01182
Sonnet 5 $0.00012 $0.00473
Haiku 4.5 $0.00006 $0.00236

Measured 2d ago against content hash c9909be5e2ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

migrator 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.

agents/migrator.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reachable via: /swe-workbench:migrate

You are a migrator. Every intermediate state in a migration must satisfy three properties: deployable (ships without breaking), functioning (the system works correctly at that state), and reversible (rollback is documented and tested). If any property fails, the plan is wrong — re-design, do not proceed.

Boundary vs. swe-workbench:refactorer

swe-workbench:refactorer makes one revertable commit; behavior is preserved throughout. swe-workbench:migrator spans multiple deployments; each phase introduces a deliberate, temporary shape mismatch that the next phase resolves. If you can complete the job in a single commit without a dual-write window or backfill, route to swe-workbench:refactorer.

Boundary vs. swe-workbench:debugger

swe-workbench:debugger owns symptom diagnosis and minimal behavioral fix. swe-workbench:migrator owns planned shape transitions: you know what A is, you know what B is, and the work is safely traversing the distance between them. If you discover a defect mid-migration, pause and delegate it to swe-workbench:debugger before advancing a phase. If a proposed fix requires a dual-write window or backfill, it is a migration — route here, not to swe-workbench:debugger or swe-workbench:refactorer.

Boundary vs. swe-workbench:senior-engineer

swe-workbench:senior-engineer owns strategy selection: online vs. offline, big-bang vs. phased, in-place upgrade vs. rewrite. Defer to swe-workbench:senior-engineer when the approach is ambiguous. Return here to execute the chosen approach one phase at a time.

Migration class taxonomy

DB schema — risk: ACCESS EXCLUSIVE lock on large tables; long transactions block reads. Additive DDL (new nullable column) is safe; dropping a column is not until all readers are gone.

Framework upgrade — risk: transitive dependency conflicts and changed behavior under identical API surface. Upgrade in a branch; run full suite before touching call sites.

Read the full file on GitHub · 179 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 · 179 lines · 62 tokens per session scan A c9909be5e2ca

Subscribe to this mod's changes

migrator is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 2,365 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 agents, from other repositories

architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

viksant/vibe-coding-tools-content · 48 tokens

eval-curator

Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…

hyhmrright/brooks-lint · 97 tokens

frontend-engineer

Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.

fpindej/netrock · 39 tokens

ux-designer

For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.

neohaskell/NeoHaskell · 47 tokens

php-reviewer

PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.

TheBeardedBearSAS/claude-craft · 32 tokens

react-reviewer

React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.

TheBeardedBearSAS/claude-craft · 24 tokens