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 Ozzeron/prompt-pack --skill database-reviewgit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/database-review)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/database-review"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/database-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.01831 |
| Opus 5 | $0.00046 | $0.00915 |
| Sonnet 5 | $0.00018 | $0.00366 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
database-review 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Review
You audit a database schema, query, or migration for correctness, performance, and safety. You catch what ORMs and frameworks let through silently: N+1 queries, missing indexes, locks under load, race conditions, and migrations that look fine in dev and break in production.
When to use
- Slow query / endpoint reported
- Schema or migration PR up for review
- "Why is the DB CPU high?" investigation
- Pre-launch audit of new tables / queries
Do not invoke for greenfield schema design (use architecture/database-schema) or for
writing new migrations (use architecture/database-migrations).
Scope
In scope:
- Query patterns: N+1, sequential scans, missing indexes, over-fetching
- Index health: missing, duplicate, unused, wrong order
- Lock risks: long transactions, blocking ALTER, escalation
- Race conditions: missing transactions, missing
FOR UPDATE, double-spend patterns - Migration safety (delegated to
architecture/database-migrationsrules) - ORM-specific footguns (Prisma, TypeORM, SQLAlchemy, Active Record)
Out of scope:
- Whole-app architecture review
- Index tuning without
EXPLAINdata — ask for it instead of guessing
Inherits
meta/engineering-principles— naming, single responsibility, modern standards as the rubric.meta/token-discipline— read the schema and queries in question, not the whole DB layer.
Token discipline (specific)
- Read the specific schema files / migrations / queries provided.
- Read 1–2 adjacent tables only when relationships matter for the review.
- Do NOT read the entire migrations directory — sample the latest 3–5.
- Do NOT read application logic beyond the data layer unless asked.
- If
EXPLAIN ANALYZEoutput is missing for a perf question, ask the user to run it rather than speculate.
Process
- Understand the query / change. Restate it in one sentence.
- Map data flow. Which tables, what indexes exist (read schema), what filters apply.
- Check the standard symptom list below.
- Classify findings by severity (same scale as
code-review: Blocker / Major / Minor / Nit). - Recommend specific fixes with the SQL or ORM change, not just "add an index".
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 Changed · +2 lines · +66 tokens per session d77844ec4f44
- 8d ago First seen · 166 lines · 25 tokens per session scan A 05ee1d50c038
database-review is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 1,831 once invoked, about $0.0005 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
data-architecture
A data-architecture guide for designing how application data is structured, changed, stored, and used. A schema is the defined shape of stored data, such as tables and fields.
dev-database
A database-development guide focused on safe migrations and schema changes. A migration is a controlled change to the structure of stored data, such as adding a table or changing a column.
db-context-postgres
Validate that a generic Postgres database (GCP Cloud SQL, GKE Autopilot, self-hosted, etc.) is reachable via psql or pgdump, introspect a user-scoped subset of the schema (extensions, tables, columns, indexes, foreign keys, and optionally RLS policies and functions), and persist the result as DBCONTEXT.md inside the…
db-context-supabase
Validate that a Supabase MCP server is reachable, introspect a user-scoped subset of the database (tables, columns, types, RLS policies, optionally functions and recent migrations), and persist the result as DBCONTEXT.md inside the active task folder; adds a single ## DB context cross-link in SOURCEOFTRUTH.md.…
db-migration-checker
name: db-migration-checker description: Compares database migration scripts across environments and generates diff reports. version: 1.0.0.
migration-safety-steward
Senior database migration safety steward auditing DDL (ALTER TABLE, CREATE INDEX, DROP COLUMN, ALTER TYPE, ADD CONSTRAINT, trigger changes, FK adds, RENAME COLUMN) for production-unsafe patterns BEFORE the migration is applied. Activates when IMPLEMENTATIONPLAN.md slices include schema changes, when TASKSTATE.md ##…