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/phuonghx/aim-cli/database-designnpx skills add phuonghx/aim-cli --skill database-designgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00089 | $0.00558 |
| Opus 5 | $0.00044 | $0.00279 |
| Sonnet 5 | $0.00018 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Design
Reason about the workload first. Patterns follow from requirements, not habit.
Load Reference Files On Demand
Each topic lives in its own file. Open only the ones the current task touches.
| File | Covers | Open it when |
|---|---|---|
database-selection.md |
Engine trade-offs across Postgres, Neon, Turso, SQLite, and friends | Picking where data lives |
orm-selection.md |
Drizzle, Prisma, Kysely, raw SQL | Picking how code talks to the DB |
schema-design.md |
Normalization, keys, relationships, soft deletes | Modeling tables |
indexing.md |
Index families and composite ordering | Speeding up reads |
optimization.md |
N+1, query plans, tuning order | Hunting down slow queries |
migrations.md |
Expand/contract, online changes, managed engines | Evolving a live schema |
Runtime Helper
A lightweight checker flags common Prisma/Drizzle schema smells. Run it; don't read it.
python scripts/schema_validator.py <project_path>
Guiding Mindset
- Surface the user's constraints (scale, latency, hosting) before committing to an engine.
- Match the tool to the actual access patterns of this project.
- Treat Postgres as a strong option, not an automatic one — a smaller store often fits better.
Pre-Build Questions
Work through these (or ask) before writing any DDL:
- Have database preferences been confirmed with the user?
- Is the engine choice justified by this project's needs?
- Does the target runtime (edge, serverless, container) shape the decision?
- Is there an index plan for the expected queries?
- Are the relationships and their cardinalities settled?
Mistakes to Steer Clear Of
❌ Reaching for Postgres on a tiny app where embedded SQLite would do
❌ Leaving frequently-filtered columns unindexed
❌ Shipping SELECT * to production paths
❌ Dumping structured fields into a JSON blob out of laziness
❌ Letting ORM relation loads fan out into N+1 query storms
What ships with it
7 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.
- yesterday First seen · 60 lines · 89 tokens per session scan A 2d95dcf4d54c
database-design is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 558 once invoked, about $0.0004 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).