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 tutur3u/platform --skill tuturuuu-databasegit clone --depth 1 https://github.com/tutur3u/platformWrote 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/tutur3u/platform/tuturuuu-database)<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-database"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-database/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/tutur3u/platform/tuturuuu-database"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-database.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 | $0.00027 | $0.00544 |
| Opus 5 | $0.00014 | $0.00272 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
tuturuuu-database 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tuturuuu Database
Core Workflow
Read references/database-checklist.md before changing schema, RLS, storage, or generated DB types.
Read references/database-api-patterns.md when the work needs the longer
database/API pattern catalog that was split out of root AGENTS.md.
Keep migrations additive when possible. Prepare migrations for the user to apply; do not run production push commands. Use runtime/API fallbacks when rollout order can vary across environments.
Use normalizeWorkspaceId(wsId) in API routes that accept workspace aliases such as personal. Keep workspace normalization consistent across selector, preview, and final save routes in the same flow.
If the user asks for commits, combine this skill with $tuturuuu-commit. Keep a
schema migration and the code that consumes it together when they are one rollout
contract; split docs-only or tooling-only follow-through only when it can be
reverted independently.
Access And Types
- Prefer importing shared DB aliases from
@tuturuuu/types/db. - Add reusable row shapes to
packages/types/src/db.tsinstead of duplicating localPick<Database...>aliases. - For type-only Supabase usage, import
TypedSupabaseClientfrom@tuturuuu/supabase/types. - Do not hand-edit generated Supabase type files.
- Avoid generic
ReturnType<typeof createAdminClient>aliases when concrete database inference matters.
API And RLS Rules
- Verify workspace membership with the request-scoped client before admin-backed child-resource lookups or mutations.
- After membership is proven, keep protected child-resource validation and writes on a consistent admin-backed, workspace-scoped path when RLS would otherwise block the operation.
- Stamp actor-owned columns explicitly when writing with service-role/admin clients.
- Handle membership lookup errors as
500; return403only when the lookup succeeds and no membership row exists. - For
auth.uid()-guarded RPCs, use the authenticated request-scoped client after permission checks instead of a service-role client.
What ships with it
3 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 Changed · -41 tokens per session adc67c04bd85
- 6d ago First seen · 46 lines · 68 tokens per session scan A abf5823d340f
tuturuuu-database is a skill published in the GitHub repository tutur3u/platform (53 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 544 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 2026-09-03.
Other skills, from other repositories
magic-ui
Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
kysely
Guidelines for developing with Kysely, a type-safe TypeScript SQL query builder with autocompletion support.
postgres-semantic-search
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector indexing, hybrid FTS/BM25 + RRF, ParadeDB, reranking, halfvec, multilingual search, query translation, and domain evals.…
golem-add-postgres-ts
Using golem:rdbms/postgres from a TypeScript Golem agent. Use when the user asks to connect to PostgreSQL, run SQL, or use PostgreSQL from TypeScript agent code.
postgres-data-modeling
Conventions for PostgreSQL with Drizzle ORM in TypeScript - schema definitions, relations, indexes, migrations with drizzle-kit, and query patterns. Use when creating or changing a Postgres table, writing queries, or debugging query performance. (Mongo projects use mongodb-data-modeling instead.).