investigating-postgres

investigating-postgres is a skill for Claude Code, Codex from jovandyaz/knowtis-app. It costs 103 tokens per session (555 once invoked), scanned A, original, MIT.

A read-only investigation tool for Knowtis PostgreSQL databases. PostgreSQL is a database system, and Knowtis is the application whose stored data it examines.

In plain words
What is it for?
Use it to inspect database structure, count or filter records, explore data, and debug issues with read-only queries.
Why use it?
It lets you answer data questions and investigate problems without changing database records, while limiting exposed personal information.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jovandyaz/knowtis-app/investigating-postgres
Any agent
npx skills add jovandyaz/knowtis-app --skill investigating-postgres
Clone the repo
git clone --depth 1 https://github.com/jovandyaz/knowtis-app

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for investigating-postgres

README.md
[![agentmods](https://agentmods.dev/badge/skills/jovandyaz/knowtis-app/investigating-postgres.svg)](https://agentmods.dev/skills/jovandyaz/knowtis-app/investigating-postgres)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00103 $0.00555
Opus 5 $0.00051 $0.00278
Sonnet 5 $0.00021 $0.00111
Haiku 4.5 $0.00010 $0.00056

Measured 4d ago against content hash c13482057026, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.agents/skills/investigating-postgres/SKILL.md · 28 lines

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)

  1. Database-enforced read-only. MCP connections must use a dedicated read-only role. Run psql investigations inside BEGIN TRANSACTION READ ONLY with ON_ERROR_STOP; if a production connection cannot prove that boundary, do not query it.
  2. 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.
  3. 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.
  4. Connection comes from the user's environment. Use pg-knowtis-local / pg-knowtis-prod or psql "$DATABASE_URL". Never construct, request, or echo credentials/connection strings.
  5. LIMIT every row-listing query (default 50). Aggregate where possible.
  6. 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.
  7. Say which database answered (local vs prod). Treat prod as sensitive: prefer local unless the question is explicitly about production.

Workflow

  1. Restate the question as the data needed.
  2. Load the schema for the tables involved (references/schema-map.md lists what lives where).
  3. Write the query with CTEs for readability; explain the join logic in one line.
  4. Execute via MCP or psql; present results as a compact table plus a one-paragraph interpretation.
  5. Empty results are an answer — report them as such; never fabricate rows.
Files

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.

Changes

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.

  1. 4d ago First seen · 28 lines · 103 tokens per session scan A c13482057026

Subscribe to this mod's changes

investigating-postgres is a skill published in the GitHub repository jovandyaz/knowtis-app (3 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 555 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.

Related

Other skills, from other repositories

escurel-platform

Use when building an application that consumes the Escurel knowledge-base service as its data store — designing a tenant's skill/instance data model, calling the agent tools…

DataZooDE/escurel · 434 tokens

wiki-export

Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", "knowledge graph export", "export to…

Ar9av/obsidian-wiki · 172 tokens

openkb-deck-neon

Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black…

VectifyAI/OpenKB · 173 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/obsidian-mcp-server · 85 tokens

api-mirror

Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.

cyanheads/obsidian-mcp-server · 68 tokens

delete-user

Remove a member from this Egregore, revoking access across GitHub, Supabase, and Neo4j. Use for /delete-user, removing or kicking someone — not inviting (/invite) or viewing members (/dashboard).

egregore-labs/egregore · 49 tokens