A migration workflow for changing databases, major dependencies, libraries, or frameworks. It includes project-specific checks such as backups, local database testing, security policies, generated types, and tests.

Use it to create and apply database migrations, upgrade packages or frameworks, update affected types, test the impact, and prepare rollback migrations.

Large technical changes can break data, security settings, or code that depends on older types and APIs. The workflow helps expose those risks and keeps already-applied database migrations unchanged.

migrate — Skill for Claude Code by GlamgarOnDiscord

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/GlamgarOnDiscord/claude-saas-blueprint

agentmods

npx agentmods add skills/glamgarondiscord/claude-saas-blueprint/migrate

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/migrate/github.svg)](https://agentmods.dev/skills/glamgarondiscord/claude-saas-blueprint/migrate)

Your own site

<a href="https://agentmods.dev/skills/glamgarondiscord/claude-saas-blueprint/migrate"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/migrate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/glamgarondiscord/claude-saas-blueprint/migrate"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 702 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.00702
Opus 5.5	$0.00010	$0.00281
Sonnet 5.5	$0.00005	$0.00140
Haiku 4.5	$0.00003	$0.00070

Measured 1mo ago against content hash f7b143d2a523, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

migrate 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 1mo 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.

.claude/skills/migrate/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modes

`/migrate db [description]` — Migration de base de données

Avant de commencer :

# 1. Backup local obligatoire
python scripts/supabase_migrate.py --diff   # voir l'état actuel
git stash || git commit -m "chore: pre-migration checkpoint"

Création et application :

python scripts/supabase_migrate.py --new [description]   # crée le fichier migration
# Éditer le fichier créé dans supabase/migrations/
python scripts/supabase_migrate.py --env local           # appliquer en dev d'abord

Checklist post-migration :

Toute nouvelle table → vérifier ENABLE ROW LEVEL SECURITY + politiques RLS
python scripts/supabase_rls_check.py — doit retourner 0 tables sans RLS
Mettre à jour core/entities/ et core/ports/ si les types changent
Régénérer les types TypeScript : pnpm supabase gen types
Tests blast radius : pnpm test -- --grep [feature]

Rollback :

python scripts/supabase_migrate.py --new rollback-[description]
# Écrire le SQL inverse dans le nouveau fichier
python scripts/supabase_migrate.py --env local

Règle stricte : jamais modifier une migration déjà appliquée — toujours créer une nouvelle.

`/migrate dep [package] [version]` — Mise à jour de dépendance majeure

Lire changelog/release notes officiel (WebSearch) — breaking changes uniquement
Grep les imports du package dans tout le projet
Appliquer les changements fichier par fichier
tsc --noEmit + tests après chaque fichier
Si la migration est complexe → /deep-update (veille changelog approfondie)
Documenter dans decisions.md si changement architecturel

`/migrate lib [ancienne] → [nouvelle]` — Changement de librairie

Rechercher le guide de migration officiel (WebSearch)
Mapper les API ancienne → nouvelle (tableau de correspondance)
EnterPlanMode — plan fichier par fichier avant de toucher quoi que ce soit
Remplacer fichier par fichier, tests verts entre chaque
pnpm remove [ancienne] seulement quand 0 import restant (Grep)
Tests complets + tsc --noEmit

Read the full file on GitHub · 73 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.

1mo ago First seen · 73 lines · 26 tokens per session scan A f7b143d2a523

Subscribe to this mod's changes

migrate is a skill published in the GitHub repository GlamgarOnDiscord/claude-saas-blueprint (2 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 702 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Databases DevOps and cloud agent-skills ai-agents cline copilot cursor

solr-extending

To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.

griddynamics/rosetta · 23 tokens

solr-semantic-search

To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.

griddynamics/rosetta · 24 tokens

solr-schema

To design and audit Solr schemas: field types, analyzers, docValues, solrconfig.

griddynamics/rosetta · 25 tokens

solr-query

To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.

griddynamics/rosetta · 27 tokens

system-design

Scalable architecture skill based on the System Design Primer. Before designing any backend, reason about load balancers, caching, DB partitioning, CAP theorem, and microservices trade-offs. Adapted for Serverless/Edge, Next.js App Router, BFF, and DDD patterns.

kok-o/contextos-agents · 61 tokens

database

Database architecture, schema design, Prisma, Drizzle ORM, indexing strategies, migrations, and N+1 query resolution.

kok-o/contextos-agents · 26 tokens