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 Morningstar202604/awesome-skillkit --skill database-designergit clone --depth 1 https://github.com/Morningstar202604/awesome-skillkitWrote 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/morningstar202604/awesome-skillkit/database-designer)<a href="https://agentmods.dev/skills/morningstar202604/awesome-skillkit/database-designer"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/database-designer/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/morningstar202604/awesome-skillkit/database-designer"><img src="https://agentmods.dev/badge/skills/morningstar202604/awesome-skillkit/database-designer.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 | $0.00077 | $0.03674 |
| Opus 5.5 | $0.00031 | $0.01470 |
| Sonnet 5.5 | $0.00015 | $0.00735 |
| Haiku 4.5 | $0.00008 | $0.00367 |
Grade A, and why
database-designer 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 1mo 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.
This is a copy
97% identical to database-designer — 306 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Design Assistant
Uses tools to support schema design and evolution: automated normalization analysis, ERD generation, index optimization based on real query patterns, and zero-downtime migration planning. It only does analysis and plan generation — it never executes schema changes against a live database.
Input Checklist
| Input | Required | Description |
|---|---|---|
| Current schema | Required | SQL DDL file or JSON schema (samples in assets/sample_schema.sql / sample_schema.json) |
| Hot query patterns | Conditionally required | Query-pattern JSON for index optimization (copy assets/sample_query_patterns.json, fill in the user's queries) |
| Target schema | Conditionally required | The second schema JSON when generating a migration |
| Database engine | Optional | PostgreSQL (SQL samples default to it), MySQL, SQLite, SQL Server |
| Multi-tenancy / RLS / seed-data needs | Optional | Triggers the schema-design-playbook workflow |
When inputs are missing, ask for all at once: "Please provide: (1) current schema (DDL file or JSON), (2) the hottest queries (for indexing), (3) the target schema if you want a migration plan, (4) target engine and tenant/RLS requirements. Everything else runs on defaults."
Pre-flight Checks
Probe one by one; on any failure → give the fix and STOP:
python3 --version # expected 3.8+; on failure: install python3
# Self-check: python3 scripts/schema_analyzer.py --help / index_optimizer.py / migration_generator.py should all exit 0; on failure: script missing → check the skill directory
test -f <schema-input> # expected exit code 0; on failure: file missing → ask the user for the DDL/JSON schema
Workflow
Use the tools; don't analyze schemas by hand. All paths are relative to this skill directory; sample inputs are in assets/.
Step 1: Analyze the schema
python3 scripts/schema_analyzer.py --input assets/sample_schema.sql --generate-erd --output-format json -o analysis.json # bundled sample DDL; swap in schema.sql for your real schema
What ships with it
16 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.
- assets/sample_query_patterns.json 9.0 KB
- assets/sample_schema.json 9.1 KB
- assets/sample_schema.sql 8.1 KB
- expected_outputs/index_optimization_sample.txt 2.6 KB
- expected_outputs/migration_sample.txt 4.4 KB
- expected_outputs/schema_analysis_sample.txt 7.3 KB
- index_optimizer.py 38 KB runs code
- migration_generator.py 49 KB runs code
- README.md 12 KB
- references/database_selection_decision_tree.md 16 KB
- references/database-design-reference.md 14 KB
- references/full-schema-examples.md 10 KB
- references/index_strategy_patterns.md 12 KB
- references/normalization_guide.md 10 KB
- references/schema-design-playbook.md 3.2 KB
- schema_analyzer.py 41 KB runs code
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.
- 1mo ago Changed · -7 tokens per session d24e8711a594
- 1mo ago Changed · -2 lines b10dbdd12f7f
- 1mo ago Changed · +1 lines · +30 tokens per session bd29b0a44e74
- 1mo ago First seen · 322 lines · 54 tokens per session scan A c20ada273be3
database-designer is a skill published in the GitHub repository Morningstar202604/awesome-skillkit (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 77 tokens to every session and 3,674 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to database-designer, differing in 306 lines, and is treated as a copy.
Other skills, from other repositories
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Quick reference for common patterns, index types, data types, and anti-pattern detection. Based on Supabase best practices.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…