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/hautc-it/cil/database-designnpx skills add hautc-it/cil --skill database-designgit clone --depth 1 https://github.com/hautc-it/cilWhat 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 | $0.00051 | $0.01114 |
| Opus 5 | $0.00026 | $0.00557 |
| Sonnet 5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
database-design 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Design Skill
Project Context
Existing project
- Read
CLAUDE.md— existing schema conventions, DB constraints, or naming rules take priority. - Identify the DB and ORM — PostgreSQL/MySQL/SQLite/MongoDB? Raw SQL, TypeORM, Prisma, SQLAlchemy, GORM? Read 2–3 existing model/schema files to understand naming (snake_case vs camelCase), primary key style (uuid vs serial), and timestamp conventions.
- Check the existing schema — new entities must follow the same patterns: column naming, index naming, foreign key style, soft-delete convention.
- Understand the migration workflow — how does this project evolve schema? (See the
migrationskill.) Design with the migration path in mind — changes that can't be migrated safely are bad designs. - Search memory —
memory_search("database schema [entity] design")— retrieve prior schema decisions, normalization choices, or known performance constraints. - Consistency with existing tables beats theoretical correctness.
Greenfield project
No schema exists yet — foundational choices here are expensive to undo:
- Choose the database and query layer together — the query layer (ORM, query builder, or raw queries) constrains which DB features you can use cleanly. Choose the pairing that fits the platform and team, not just the DB in isolation.
- Set naming conventions before the first table — decide and document:
- Table/collection naming style (singular vs plural, casing)
- Primary key style (auto-increment integer, UUID, or platform-specific)
- Timestamp columns (
created_at,updated_aton every record;deleted_atif soft-delete is needed) - Foreign key naming pattern
- Do the access pattern analysis first (see Protocol step 1 below) — schema designed without knowing the read/write queries will need expensive rework.
- Design for migration — columns should be nullable or have cheap defaults so future schema changes don't require table rewrites or long locks.
- Write conventions into
CLAUDE.md— naming rules, primary key style, soft-delete approach. This prevents divergence as the codebase grows. - Store the decisions:
memory_store("decision", "db: [database]+[query layer], PKs=[style], naming=[style], soft-delete=[x]", ["database", "schema", "conventions"])
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.
- 2d ago First seen · 100 lines · 51 tokens per session scan A 9c04b6a3cd08
database-design is a skill published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,114 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 2026-08-31.
Other skills, from other repositories
caching
Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache. Use when implementing or reviewing caching logic.
database-optimizer
Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.
cli-audit-data
Audit PostgreSQL database safety in Rust/SQLx applications. Use for schemas, migrations, constraints, indexes, transactions, repositories, state transitions, idempotency, concurrency, queues, multi-tenancy, soft deletion, ledgers, auditability, repair, database incidents, or whenever SQLx and PostgreSQL changes could…
cli-forge-data
Design and implement safe PostgreSQL database changes for Rust/SQLx applications. Use for new schemas, migrations, constraints, indexes, repositories, transaction boundaries, state machines, idempotency, concurrency control, queues, multi-tenancy, soft deletion, ledgers, outbox/inbox, repair jobs, or corrections…
postgres-pro
Use when optimizing PostgreSQL queries, configuring replication, or implementing advanced database features. Invoke for EXPLAIN analysis, JSONB operations, extension usage, VACUUM tuning, performance monitoring.
sql-pro
Use when optimizing SQL queries, designing database schemas, or tuning database performance. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis.