Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/db-auditWrote 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/greglas75/zuvo/db-audit)<a href="https://agentmods.dev/skills/greglas75/zuvo/db-audit"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/db-audit/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/greglas75/zuvo/db-audit"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/db-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 246 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Anti-Refusal · line 762 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Excessive Agency · line 49 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Rogue Agent · line 157 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 1020 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00115 | $0.17866 |
| Opus 5.5 | $0.00046 | $0.07146 |
| Sonnet 5.5 | $0.00023 | $0.03573 |
| Haiku 4.5 | $0.00012 | $0.01787 |
Grade A, and why
db-audit scanned grade A with 1 finding 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 2d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Worktree de-pollution (do this before ANY file/table/migration count).** If the repo has git worktrees checked out under the tree (`.worktrees/`, `.claude/worktrees/`, `worktrees/`), every `.sql`/migration/model file i Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 1,164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:db-audit
Audit database interactions from code patterns through schema design to live query plans. Produces a scored report with specific, actionable fixes ranked by impact and effort.
When to use: Before releases, after adding models or queries, when latency
increases, after scaling incidents, periodic health check.
When NOT to use: Code quality (zuvo:review), full-stack performance
(zuvo:performance-audit), security-only (/security-audit).
Mandatory File Loading
Read every file below before starting. Print the checklist.
CORE FILES LOADED:
1. ../../shared/includes/codesift-setup.md -- [READ | MISSING -> STOP]
2. ../../shared/includes/env-compat.md -- [READ | MISSING -> STOP]
3. ../../shared/includes/run-logger.md -- [READ | MISSING -> STOP]
Deferred (lazy load):
DEFERRED FILES (read only when needed):
- ../../shared/includes/retrospective.md -- read right before Phase 6 (saves ~3K tokens during audit)
Note: cq-patterns.md is NOT loaded — this is a read-only audit, not a code quality review. Loading it wastes ~7K tokens per turn.
If any CORE file is MISSING, STOP. Do not proceed from memory.
MANDATORY TOOL CALLS — Audit Validity Gate
This audit is INVALID if any of the tools below are skipped when their trigger condition holds. "DEFERRED", "N/A", "no diff vs prior audit" are NOT valid reasons. The presence of trigger artifacts (migrations directory, .sql files, ORM schema, etc.) is what dictates the call — not whether they changed since the last audit.
Required tool list
| Tool | Trigger | Reason | Skip allowed? |
|---|---|---|---|
sql_audit |
Project has any .sql file (migrations, schema, dumps) anywhere under TARGET_ROOT |
DB6/DB12/DB13 — bundles 5 gates (drift, orphan, lint, dml, complexity) that no manual scan reproduces | NO — audit FAILS if skipped while trigger holds |
analyze_schema |
Same as sql_audit (.sql files exist) |
DB3 schema design — extracts tables/columns/FKs/relationships, generates ERD for executive summary | NO when .sql exists |
diff_migrations |
migrations/ dir exists (any ORM/framework) |
DB6/DB13 deployment safety — classifies every op as additive/modifying/destructive with risk ranking; surfaces destructive ops missed by sql_audit lint gate |
NO when migrations exist |
trace_query |
At least one HIGH/MEDIUM finding mentions a table OR sql_audit orphan gate flags any orphan |
DB3/DB13 verification — confirms zero references for "orphan" claim and traces every cited table across DDL/DML/FK/ORM (Prisma + Drizzle) | NO when condition holds |
search_columns |
Always | DB12 PII discovery — find every email/password/ssn/token column across all tables |
NO — always required |
migration_lint |
Postgres detected (any of: pg, psycopg2, @prisma/adapter-pg, postgres-js in deps) AND migrations/ dir exists |
DB13 migration deployment safety (squawk: 30+ PG-specific patterns including NOT NULL without default, CREATE INDEX without CONCURRENTLY, etc.) |
NO when both conditions hold |
analyze_prisma_schema |
prisma/schema.prisma exists |
DB2/DB3/DB6 Prisma-specific schema gates (FK index coverage %, unindexed FKs, soft-delete detection, status: String smell) |
NO when schema exists |
explain_query |
Prisma project AND any HIGH/MEDIUM finding cites a prisma.<model>.<call> query |
DB1/DB2 Prisma-specific N+1 + missing-index detection via simulated EXPLAIN ANALYZE; finds risks sql_audit dml cannot see |
NO when condition holds |
python_audit |
Language detected as Python | DB1 N+1 detection (n-plus-one-django pattern), DB9 ORM anti-patterns |
NO when Python project |
nest_audit |
Framework detected as NestJS (@nestjs/* in deps) |
DB1/DB4 NestJS DI + repository scoping issues | NO when NestJS project |
analyze_django_settings + get_model_graph |
django in pyproject/requirements |
DB6 Django migration safety, DB3 model graph | NO when Django |
scan_secrets |
Always | DB12 hardcoded credentials in code or .env |
NO — always required |
search_patterns(pattern="unbounded-findmany") + search_patterns(pattern="await-in-loop") + search_patterns(pattern="toctou") |
Always | DB1/DB5 — these are the ONLY tool-verified gates for those patterns | NO — always required |
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.
- 2d ago Changed · +6 lines 8e8658faec95
- 1mo ago Changed · -2 lines 0efd2f8b2761
- 1mo ago First seen · 1,160 lines · 115 tokens per session scan A b7a0bd4435f7
db-audit is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 17,866 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ring:using-lib-systemplane
Using lib-systemplane, the hot-reload runtime-config plane (Postgres LISTEN/NOTIFY or MongoDB change streams), in two modes. Sweep Mode detects DIY config reload (SIGHUP, fsnotify, viper, pgx LISTEN), manual tenant-scoping, hand-built admin CRUD, and v4 residue. Reference Mode catalogs client lifecycle and…
ring:using-outbox
Using the transactional-outbox pattern across lib-streaming (writer) and lib-commons/v5/commons/outbox (repository + relay), in two modes. Sweep Mode detects DIY outbox tables, hand-rolled relay loops, send-and-pray emits, missing WithOutboxTx wrapping, and broker calls inside DB transactions. Reference Mode catalogs…
ring:mapping-service-resources
Mapping a Go service's Service -> Module -> Resource hierarchy for dispatch-layer registration: detects modules and per-module PostgreSQL/MongoDB/RabbitMQ resources, database names, and shared databases, generates MongoDB index migration pairs (.up.json/.down.json), detects existing Postgres migrations, emits an HTML…
ring:designing-data-model
Designing the physical data model as a real stack-native schema (schema.sql with CREATE TABLE DDL, indexes, and constraints for Postgres/Go; schema.prisma for Prisma/TS; Postgres schema.sql as fallback) from the Gate 4 OpenAPI spec and TRD. Gate 5 of ring:planning-large-features; runs after…
align-docs
Align stale repository docs and task records; use --clean for a full documentation cleanup.
changelog
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.