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 agentmods add skills/monkilabs/opencastle/drizzlenpx skills add monkilabs/opencastle --skill drizzlegit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/drizzle)<a href="https://agentmods.dev/skills/monkilabs/opencastle/drizzle"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/drizzle.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.00513 |
| Opus 5 | $0.00034 | $0.00257 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
drizzle-orm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Drizzle ORM
Gotchas
drizzle(client, { schema })— omit{ schema }and thedb.query.*relational API silently does not exist.relations()is ORM-level metadata only and creates no constraint. Definereferences(() => users.id, { onDelete: 'cascade' })as well; you need both.- Types come from
typeof table.$inferSelect/$inferInsert— never hand-write them. - SQL-like API (
db.select().from()) for joins and aggregates; relational API (db.query.x.findMany({ with: {...} })) for nested reads.insert/update/deletegive back nothing usable without.returning(). - Inside
db.transaction(async (tx) => ...)every call must usetx; a straydbcall runs outside the transaction. - Prepared statements need
sql.placeholder('id')+.prepare('name'), then.execute({ id }). - Partial selects (
db.select({ id: users.id })) avoid loading unused columns; declare indexes in the table definition.
drizzle-kit
generate→ review the SQL in theoutdir →migrate.pushis dev-only. Never edit generated SQL; fix the schema and regenerate.checkvalidates migration history consistency.- A column rename generates DROP + ADD, i.e. data loss. Hand-write the migration file instead —
ALTER TABLE users RENAME COLUMN old_name TO new_name;— thenmigrateapplies it. - A new non-nullable column takes two migrations: add nullable → backfill → add
.notNull()→ migrate again. - The programmatic migrator needs a single connection:
postgres(url, { max: 1 }), thenmigrate(drizzle(client), { migrationsFolder: './drizzle' }), then close it. drizzle.config.tsmust supplydialect,schema,out, anddbCredentials.urlbefore any command runs.
What ships with it
1 file 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.
- 4d ago First seen · 27 lines · 69 tokens per session scan A 7a7e37481dab
drizzle-orm is a skill published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 6d ago), licensed MIT. It adds 69 tokens to every session and 513 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 2026-08-30.
Other skills, from other repositories
architecture-database-design
Master of PostgreSQL schema design, optimization, and safe migrations. Enforces strict conventions for IDs, indexes, JSONB, and transactional DDL. Use whenever modifying the data layer.
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
dinero-currency-patterns
Currency handling patterns for the Dinero.js money library. Use when working with multiple currencies, converting between currencies, defining custom currencies, storing monetary values in databases, or integrating with payment services like Stripe or PayPal. Triggers on currency conversion, database schema design for…
ai-persistence/stores
Implement the MessageStore, RunStore, InterruptStore, MetadataStore contracts for @tanstack/ai-persistence against any database. defineAIPersistence, composePersistence overrides, critical invariants (full-replace saveThread, insert-if-absent createOrResume and interrupt create), authorize thread access…
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…
system-table-change
Use when adding, removing, or modifying columns/indexes on system tables. Provides a checklist covering schema definitions, migrations, version gates, golden files, and test hashes.