Borrowing it
Nothing to install: this file belongs to jovandyaz/knowtis-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jovandyaz/knowtis-app/main/.agents/skills/investigating-postgres/SKILL.mdgit clone --depth 1 https://github.com/jovandyaz/knowtis-appWrote 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/jovandyaz/knowtis-app/investigating-postgres)<a href="https://agentmods.dev/skills/jovandyaz/knowtis-app/investigating-postgres"><img src="https://agentmods.dev/badge/skills/jovandyaz/knowtis-app/investigating-postgres/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/jovandyaz/knowtis-app/investigating-postgres"><img src="https://agentmods.dev/badge/skills/jovandyaz/knowtis-app/investigating-postgres.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 | $0.00103 | $0.00555 |
| Opus 5.5 | $0.00041 | $0.00222 |
| Sonnet 5.5 | $0.00021 | $0.00111 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
investigating-postgres scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Investigating Postgres (read-only)
Answer data questions against Knowtis databases without ever mutating them. The full contract is in references/read-only-contract.md; the table map is in references/schema-map.md.
Contract (non-negotiable)
- Database-enforced read-only. MCP connections must use a dedicated read-only role. Run psql investigations inside
BEGIN TRANSACTION READ ONLYwithON_ERROR_STOP; if a production connection cannot prove that boundary, do not query it. - SELECT/WITH only. A CTE must end in a read-only SELECT. No INSERT, UPDATE, DELETE, TRUNCATE, DDL, mutating CTE, or session-changing
SET. Redirect mutations to APIs, migrations, or the application. - Schema first. Read
apps/api/src/database/schema/(or the MCP schema tools) before writing SQL — column names come from the source of truth, not from memory. - Connection comes from the user's environment. Use
pg-knowtis-local/pg-knowtis-prodorpsql "$DATABASE_URL". Never construct, request, or echo credentials/connection strings. - LIMIT every row-listing query (default 50). Aggregate where possible.
- Redact PII by default in output: user emails, note titles/content, session tokens, provider keys. Show them only on explicit request and never against prod without confirmation.
- Say which database answered (local vs prod). Treat prod as sensitive: prefer local unless the question is explicitly about production.
Workflow
- Restate the question as the data needed.
- Load the schema for the tables involved (references/schema-map.md lists what lives where).
- Write the query with CTEs for readability; explain the join logic in one line.
- Execute via MCP or psql; present results as a compact table plus a one-paragraph interpretation.
- Empty results are an answer — report them as such; never fabricate rows.
What ships with it
4 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.
- 1mo ago First seen · 28 lines · 103 tokens per session scan A c13482057026
investigating-postgres is a skill published in the GitHub repository jovandyaz/knowtis-app (4 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 555 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
prisma-schema-conventions
Data modeling conventions for Prisma + PostgreSQL in multi-tenant systems — workspace isolation, numeric criticality, idempotent recurrence, document versioning by lineage and decoupled audit via a queue in Postgres itself. Use whenever creating or changing schema.prisma, designing new entities, planning migrations or…
nestjs-security-isolation
Enforce multi-tenant isolation and PostgreSQL Row Level Security in NestJS. Use when enforcing tenant isolation or PostgreSQL RLS in NestJS multi-tenant apps.
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.