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.
npx skills add slbug/claude-ruby-grape-rails --skill safe-migrationsgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWrote 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/skills/slbug/claude-ruby-grape-rails/safe-migrations)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/safe-migrations"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/safe-migrations/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/skills/slbug/claude-ruby-grape-rails/safe-migrations"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/safe-migrations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.02026 |
| Opus 5.5 | $0.00022 | $0.00810 |
| Sonnet 5.5 | $0.00011 | $0.00405 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
safe-migrations 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.
How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Migrations
Scope Check First
This skill is Active Record-first unless the touched package clearly uses Sequel.
Before giving migration advice, identify which migration system owns the file:
class ... < ActiveRecord::Migration[...]→ Active Record migrationSequel.migration do→ Sequel migration- mixed repos may contain both
If the repo is modular or mixed-ORM:
- identify the owning package first
- do not generate Rails migration templates for Sequel packages
- do not assume one global migration strategy for the whole repository
Iron Laws
- Never drop columns/tables while code references them
- Never add column with default on large tables (PG < 11, MySQL)
- Never add index non-concurrently on large tables
- Never change column type on large tables
- Never rename without multi-step process
- Always backfill in batches
The Three-Step Deployment Process
Deploy 1: Add new structure (nullable, no default)
Deploy 2: Update code; backfill data; switch reads
Deploy 3: Remove old structure; add constraints
Locking Behavior Note
Warnings like "locks table" are generalizations — actual locking behavior varies by database:
| Database | Concurrent Indexes | DDL Transaction Safety | Notes |
|---|---|---|---|
| PostgreSQL 11+ | CONCURRENTLY supported |
disable_ddl_transaction! required |
Best for zero-downtime |
| PostgreSQL < 11 | CONCURRENTLY supported |
Same as above | Adding column with default locks table |
| MySQL 8.0+ | No concurrent option | pt-online-schema-change for large tables |
InnoDB has different locking model |
| MySQL 5.7 | No concurrent option | Use percona toolkit | More locking on DDL |
| SQLite | N/A (file-based) | Locks entire database | Development/test only |
Always consult your database documentation for exact locking behavior. See references/database-specific.md for detailed guidance.
Safe Patterns
Adding a Column
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 271 lines · 55 tokens per session scan A 9dafb2ca9974
safe-migrations is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 2,026 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
omh-relational-db
This is an OMH relational-db workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-sqli-detail-pack
Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
data-governance
Use this skill when designing or reviewing data governance: schema ownership, PII handling, retention, lineage, access policy, and migration safety for services and data stores. Triggers: user says "data governance", "PII", "schema ownership", "retention policy", "data lineage", "migration safety".
backup-recovery
Design and verify backups and restoration for owned databases, files and application state. Use when preparing recovery, migrating data or testing backups; protect the source and prove restore into an isolated destination before calling recovery ready.