pg-aiguide CLAUDE.md

pg-aiguide CLAUDE.md is an instructions file for coding agents from timescale/pg-aiguide. It costs 419 tokens per session, scanned A, original, Apache-2.0.

Development instructions for the Tiger Docs MCP server, a service that lets an agent access tools through a standard connection. They cover building, running, testing, TypeScript style, validation, and error handling.

In plain words
What is it for?
Use them when developing, checking, or running the Tiger Docs server.
Why use it?
They keep server changes consistent with the project’s required commands and coding conventions.

Instructions file

About the project

pg-aiguide is a knowledge and tooling project that gives AI coding assistants version-aware PostgreSQL documentation and curated database practices. Developers use it through agent skills, an MCP server, or a Claude Code plugin to help coding tools generate better PostgreSQL code. The catalogue entries are its skills, instructions, MCP integration, and rule.

timescale/pg-aiguide · 1,835 stars · on GitHub

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 instructions/timescale/pg-aiguide/claude-md
Clone the repo
git clone --depth 1 https://github.com/timescale/pg-aiguide

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 pg-aiguide CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timescale/pg-aiguide/claude-md.svg)](https://agentmods.dev/instructions/timescale/pg-aiguide/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timescale/pg-aiguide/claude-md"><img src="https://agentmods.dev/badge/instructions/timescale/pg-aiguide/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 419 This file is loaded in full into every session.
When invoked 419 The same file — it is already loaded in full.
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 $0.00419 $0.00419
Opus 5 $0.00210 $0.00210
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash f971da0ef30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pg-aiguide CLAUDE.md 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 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.

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.

CLAUDE.md · 33 lines

What it actually says

Tiger Docs MCP Server - Development Guidelines

Build, Test & Run Commands

  • Build: ./bun run build - Compiles TypeScript to JavaScript
  • Watch mode: ./bun run watch http - Watches for changes and rebuilds automatically
  • Run server: ./bun run start stdio - Starts the MCP server using stdio transport
  • Checks: ./check - All-in-one command to lint and test. Run before every commit. Covers TypeScript (biome, tsc, tests) and Python (ruff format + ruff check in ingest/). Python checks are skipped with a warning if uv is missing.

Code Style Guidelines

  • Use ES modules with .js extension in import paths
  • Strictly type all functions and variables with TypeScript
  • Follow zod schema patterns for tool input validation
  • Use .nullable() instead of .optional() for optional MCP tool parameters (required for gpt-5 compatibility)
  • Prefer async/await over callbacks and Promise chains
  • Place all imports at top of file, grouped by external then internal
  • Use descriptive variable names that clearly indicate purpose
  • Implement proper cleanup for timers and resources in server shutdown
  • Follow camelCase for variables/functions, PascalCase for types/classes, UPPER_CASE for constants
  • Handle errors with try/catch blocks and provide clear error messages
  • Use consistent indentation (2 spaces) and trailing commas in multi-line objects

Python (ingest/)

  • Formatted and linted by ruff; config lives in ingest/pyproject.toml
  • Never commit generated artifacts (__pycache__/, *.pyc, .venv/, .ruff_cache/)
  • Add dev-only tooling to the dev dependency group, not dependencies
  • Commit the regenerated uv.lock whenever dependencies change; CI runs uv lock --check
  • Chain re-raised exceptions with raise ... from e to preserve the original traceback
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. 2d ago Changed · +10 lines · +157 tokens per session f971da0ef30d
  2. 5d ago First seen · 23 lines · 262 tokens per session scan A a6435d5eb457

Subscribe to this mod's changes

pg-aiguide CLAUDE.md is an instructions file published in the GitHub repository timescale/pg-aiguide (1,835 stars, last pushed today), licensed Apache-2.0. It adds 419 tokens to every session, about $0.0021 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 2026-08-30.