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.
git clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWrote 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/commands/ruslan-korneev/claude-plugins/migrate-create)<a href="https://agentmods.dev/commands/ruslan-korneev/claude-plugins/migrate-create"><img src="https://agentmods.dev/badge/commands/ruslan-korneev/claude-plugins/migrate-create/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/commands/ruslan-korneev/claude-plugins/migrate-create"><img src="https://agentmods.dev/badge/commands/ruslan-korneev/claude-plugins/migrate-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00018 | $0.00934 |
| Opus 5.5 | $0.00007 | $0.00374 |
| Sonnet 5.5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
migrate:create 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command /migrate:create
Create an Alembic migration with automatic fixing of problematic types.
Principle
Alembic does not always correctly generate downgrade for:
- Enum types — creates in upgrade, but does NOT delete in downgrade
- Array types — problems when changing element type
- JSON/JSONB — nullable changes require data migration
Instructions
Step 1: Create migration
alembic revision --autogenerate -m "{{ message }}"
Step 2: Find the created file
ls -la alembic/versions/*.py | head -1
Step 3: Check and fix migration
Enum types
Problem: Alembic creates enum in upgrade, but does not delete in downgrade.
Auto-fix:
# Find all enums in the file
# Pattern: sa.Enum("value1", "value2", name="enum_name")
If enum is found:
# Add at the beginning of the file
status_type = sa.Enum("pending", "active", "inactive", name="status_type")
def upgrade() -> None:
# status_type is created automatically when creating the column
op.create_table(
"users",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("status", status_type, nullable=False),
sa.PrimaryKeyConstraint("id"),
)
def downgrade() -> None:
op.drop_table("users")
# IMPORTANT: Delete enum type
status_type.drop(op.get_bind(), checkfirst=False)
Adding column with enum
# upgrade
def upgrade() -> None:
status_type = sa.Enum("pending", "active", name="status_type")
status_type.create(op.get_bind(), checkfirst=True)
op.add_column(
"users",
sa.Column("status", status_type, nullable=True),
)
# downgrade
def downgrade() -> None:
op.drop_column("users", "status")
# Enum remains if used in other tables
# sa.Enum(name="status_type").drop(op.get_bind(), checkfirst=True)
Array types
# When changing array element type
def upgrade() -> None:
# First delete old column
op.drop_column("users", "tags")
# Create with new type
op.add_column(
"users",
sa.Column("tags", sa.ARRAY(sa.String(100)), nullable=True),
)
def downgrade() -> None:
op.drop_column("users", "tags")
op.add_column(
"users",
sa.Column("tags", sa.ARRAY(sa.String(50)), nullable=True),
)
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 · 174 lines · 18 tokens per session scan A 6b34b7ca01a0
migrate:create is a command published in the GitHub repository ruslan-korneev/claude-plugins (5 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 934 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.
Other commands, from other repositories
db
A read-only database consultation command covering SQL Server, SQLite, and PostgreSQL, which are systems for storing structured application data.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
guide
Ask the plugin about itself — what a config key does, how the plan gate grades, what the journal can prove — answered from its own docs with a citation for every claim, by the read-only guide agent.
data-flow-analysis
Trace how data flows through the system from input to output.