Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add int2t05/engineering-skills/plugin install engineering-skillsWrote 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/int2t05/engineering-skills/schema-design)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/schema-design"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/schema-design.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 5.1 | $0.00062 | $0.01515 |
| Opus 5 | $0.00031 | $0.00758 |
| Sonnet 5 | $0.00012 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
schema-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 6d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema Design
Design the data model that sits beneath the API and beside the domain language. architecture
picks the datastore type; domain-modeling sharpens the vocabulary; this skill designs the actual
shape of the data — entities, relationships, indexes, constraints, and how the model scales. A
schema designed reactively (added-to-as-features-arrive) becomes a performance and correctness
liability that is expensive to fix later.
When to use
- Designing entities and relationships for a new feature or bounded context
- Choosing normalization level, indexing strategy, or partitioning for a new model
- Reviewing a proposed schema for correctness, performance, or future evolution
- Triggers on "data model", "schema design", "database design", "ER model", "数据模型", "表结构设计", "数据库设计"
Scope: assumes a relational datastore (Postgres/MySQL/SQLite). For document stores (MongoDB), key-value (DynamoDB), or graph stores, the embedding-vs-referencing and sharding decisions differ — use
architecturefor datastore selection, then adapt these patterns.
Not for: choosing the datastore type (use architecture); ubiquitous-language glossary (use
domain-modeling); API request/response shapes (use api-design); changing an existing schema
in production (use deprecation-migration).
Steps
1. Map entities and relationships
Start from the domain model (domain-modeling output / CONTEXT.md) and translate nouns into
entities, verbs into relationships. For each entity, identify its identity (primary key), its
attributes, and its lifecycle (created, mutated, archived, deleted).
- Draw an ER diagram (Mermaid erDiagram — see
${CLAUDE_PLUGIN_ROOT}/references/mermaid-diagrams.md) - Cardinality for every relationship: one-to-one, one-to-many, many-to-many
- Resolve many-to-many with junction tables; never hide them in a comma-separated column
Verify: every entity in the domain model is represented; every relationship has documented cardinality.
What ships with it
2 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.
- 6d ago First seen · 125 lines · 62 tokens per session scan A 95015ef22cb3
schema-design is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 1,515 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
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…
pr-workflow
Crear pull requests completas con descripcion, labels y reviewers.
laravel-vector-search
Use when implementing semantic/vector search in Laravel 13 with PostgreSQL + pgvector.
review-prompt
Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.