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 niels-emmer/myace --skill schema-designgit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/schema-design)<a href="https://agentmods.dev/skills/niels-emmer/myace/schema-design"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/schema-design/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/niels-emmer/myace/schema-design"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/schema-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00505 |
| Opus 5 | $0.00013 | $0.00253 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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.
What it actually says
Purpose
A schema is the longest-lived artifact in most systems — it outlives every framework and most of the code that reads it. This skill is a checklist for designing schemas that stay easy to evolve: additive by default, constraint-driven, and explicit about the decisions that are hard to reverse.
When to use it
Whenever you're designing a new table, changing an existing one, or reviewing a schema change. The discipline matters most for tables that will accumulate data and consumers over time.
Checklist
- Additive by default. New columns are nullable or have a default; new tables are created empty. A breaking change (rename, drop, type change) is a deliberate, reviewed decision with a migration path — not an accident of editing a column.
- Constraints over convention. Enforce invariants with foreign keys, uniqueness, check constraints, and not-null wherever the DB can express them. If an invariant can be violated by any code path that forgets it, it belongs in the DB.
- Explicit soft vs. hard delete. Decide per entity, and make the decision visible. Soft-delete columns need to be filtered everywhere; hard-delete is irreversible. Don't default to one silently.
- Types match meaning. Use the narrowest type that fits the data (dates as dates, not strings; money as a decimal, not a float). A type that's too loose invites bugs that are hard to find later.
- Keys are stable. Prefer surrogate keys that never change meaning. A natural key that can change (email, username) makes a poor primary key.
- Naming is consistent. One convention for table/column/index names across the schema. A new table that drifts from the surrounding naming is a review finding, not a style preference.
Expected output
A schema that a developer familiar with the system can extend without guessing: new columns are additive, invariants are enforced by the DB, delete semantics are explicit per entity, and the naming/typing is consistent with everything around it.
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 · 28 lines · 25 tokens per session scan A fbfb94dd02b0
Schema Design is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 505 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
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
parallel-design-variants
A workflow for producing several genuinely different visual design directions at the same time. It uses distinct visual references, gathers the results into a comparison gallery, and can support choosing winners before another design round.
loom-database-design
Database schema and data model design for relational, NoSQL, time-series, and warehouse systems.
loom-sql-optimization
Analyzes and optimizes SQL queries for performance.
loom-accessibility
Web accessibility patterns, WCAG compliance, and inclusive design.