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 kensaurus/cursor-kenji --skill audit-db-schemagit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/audit-db-schema)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-db-schema"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-db-schema/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/kensaurus/cursor-kenji/audit-db-schema"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-db-schema.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.04149 |
| Opus 5.5 | $0.00022 | $0.01660 |
| Sonnet 5.5 | $0.00011 | $0.00830 |
| Haiku 4.5 | $0.00006 | $0.00415 |
Grade A, and why
audit-db-schema 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 27d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Schema Audit Skill
Degree of freedom: MIXED — Steps 0, 1, 3 [HIGH freedom]; Steps 2 and 4
MCP/SQL probes [LOW freedom — run exactly] (run the query; do not invent a schema).
How to reason
- Observe — quote the column, constraint, advisor row, or query result
- Interpret — what fails at write-time, read-time, or migrate-time?
- Classify — naming / type / constraint / index / RLS / migration / correct
- Severity — missing FK/RLS on public data = P0; type/index drift = P1; naming = P2
Worked example
Observe:
orders.user_idis nullabletext, no FK, no index;rowsecurity = false. Interpret: orphan rows can insert; the client can SELECT every order; lookups seq-scan. Classify: constraint + index + RLS (not a naming nit). Severity: P0 — public table, no RLS, no FK. Finding:orders| RLS+FK | P0 | enable RLS +user_id uuid references users(id)+ index.
Self-critique before reporting [LOW freedom — do not skip]
- Evidenced — query result or advisor URL, not "Postgres usually…"
- Reproducible — same SQL twice; do not cite a stale
list_tables - Severity justified — P0 = data loss, leak, or unconstrained money type
- Right owner — who-can-read-what →
plan-rls-audit; DELETE/TRUNCATE →plan-data-integrity; RPO →plan-backup-dr - No migrations applied — findings only
Step 0: Auto-Detect Database Environment
0a. Detect Database and ORM
| Signal | Technology |
|---|---|
@supabase/supabase-js in package.json |
Supabase (Postgres) |
prisma in devDependencies, prisma/schema.prisma |
Prisma ORM |
drizzle-orm in dependencies, drizzle/ directory |
Drizzle ORM |
sequelize in dependencies |
Sequelize ORM |
sqlalchemy in requirements |
SQLAlchemy (Python) |
supabase/migrations/*.sql directory |
Supabase migrations |
prisma/migrations/ directory |
Prisma migrations |
drizzle/migrations/ or drizzle/*.sql |
Drizzle migrations |
What ships with it
1 file 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.
- 27d ago Changed · -9 lines · -11 tokens per session 5457dd5e0e21
- 1mo ago First seen · 475 lines · 66 tokens per session scan A b07350c2cc2d
audit-db-schema is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 4,149 once invoked, about $0.0002 per session on Opus 5.5. 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
create-migration
Create a new database migration following project naming and safety rules. Use when the user asks to add a migration or create a migration for a schema change.
opensearch
Workflow for OpenSearch (or Elasticsearch) usage: indexing, search, mappings, and tuning. Use when the user asks about OpenSearch/Elasticsearch.
data-integrity-auditor
Detects data integrity issues including orphaned records, broken foreign key relationships, constraint violations, and provides automated fix migrations. Use for "data integrity", "orphaned records", "broken relationships", or "data quality".
integration-test-builder
Creates integration tests for API endpoints with database flows, including test harness setup, fixtures, setup/teardown, database seeding, and CI-friendly strategies. Use for "integration testing", "API tests", "database tests", or "test harness".
data-retention-archiving-planner
Plans and implements data retention policies with archival strategies, compliance requirements, automated cleanup jobs, and cold storage migration. Use for "data retention", "data archival", "GDPR compliance", or "storage optimization".
data-seeding-fixtures-builder
Generates deterministic seed data for development and testing with factory functions, realistic fixtures, and database reset scripts. Use for "data seeding", "test fixtures", "database seeding", or "mock data generation".