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/nevaberry/nevaberry-plugins/drizzle-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill drizzle-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWhat 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 | $0.00010 | $0.01559 |
| Opus 5 | $0.00005 | $0.00779 |
| Sonnet 5 | $0.00002 | $0.00312 |
| Haiku 4.5 | $0.00001 | $0.00156 |
Grade A, and why
drizzle-knowledge-patch 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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drizzle ORM Knowledge Patch
Use this skill when work touches Drizzle SQL identifiers or aliases, Drizzle Kit module loading, or Zod schemas generated from Drizzle tables.
The relevant behavior is controlled by different packages and, for the CLI, by the runtime used to launch it. Establish those boundaries before changing code or dependencies.
Working method
Before editing:
- Read the installed
drizzle-ormversion. - Read the installed
drizzle-kitversion separately. - Identify whether Drizzle Kit is launched with Node, Bun, or Deno.
- Search for
sql.identifier()andsql.as()calls. - Search for imports from
drizzle-zodanddrizzle-orm/zod. - Confirm whether
zodis a direct application dependency. - Open the task-specific reference below before selecting a change.
Do not use the ORM version to infer CLI loader behavior.
Do not use the Drizzle Kit version to infer schema-generator availability.
Do not assume every JavaScript runtime follows the Node loader path.
Reference index
| Reference | Topics | Read when |
|---|---|---|
| queries-and-runtime.md | Identifier and alias escaping; SQL injection risk | Reviewing or changing sql.identifier() or sql.as() |
| migrations-and-kit.md | Runtime-aware Drizzle Kit loading; ESM and CommonJS | Running the CLI or diagnosing module-loading failures |
| schema-validation.md | Built-in Zod generators; deprecated package; direct dependency | Creating or migrating select, insert, or update schemas |
Quick reference
Upgrade code that constructs identifiers or aliases
Current Drizzle ORM releases properly escape values passed to
sql.identifier() and sql.as().
Earlier releases could leave those values improperly escaped and expose an application to SQL injection.
If either helper is present, verify the installed ORM and upgrade from an affected release. Treat this as a security change, not routine cleanup.
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.
- 3d ago First seen · 203 lines · 10 tokens per session scan A cbf007e3da14
drizzle-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 1,559 once invoked, about $0.0001 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
api-database-postgresql
Direct PostgreSQL access with node-postgres (pg) -- connection pools, parameterized queries, transactions, streaming, LISTEN/NOTIFY, error handling.
api-database-sequelize
Sequelize ORM, model definitions, associations, queries, transactions, migrations.
api-database-typeorm
Decorator-based ORM for TypeScript with Active Record and Data Mapper patterns.
api-database-drizzle
Drizzle ORM, queries, migrations.
om-migrate-mikro-orm
Migrate custom module code from MikroORM v6 to v7. Fixes v7 type errors (FilterQuery, RequiredEntityData), replaces Knex raw queries with Kysely, migrates persistAndFlush/removeAndFlush, updates decorator imports. Triggers on "mikro-orm v7", "persistAndFlush deprecated", "knex to kysely".
pinme-email
Use this skill when a PinMe project (Worker TypeScript) needs to integrate email sending (sendemail). Guides AI to generate correct Worker TS code.