agentmods.dev

MCPg: Instructions file for Claude Code

CLAUDE.md

MCPg CLAUDE.md is an instructions file for Claude Code from devopam/MCPg. It costs 1,559 tokens per session, scanned A, original, MIT.

Repository instructions for MCPg, a PostgreSQL database server that exposes database operations to AI assistants through MCP. PostgreSQL is a relational database system, and MCP is a standard for connecting assistants to tools.

In plain words
What is it for?
Use them when changing, testing, documenting, packaging, or checking the safety rules of the MCPg server.
Why use it?
They point the coding agent to the project's source of truth and emphasize checking claims against the code, command line, or live service.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is devopam/MCPg's own configuration. It tells Claude Code how to work on MCPg itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MCPg configures →

not rated 14repo changed today A scan 1,559 tokens original MIT
View source ↗ devopam/MCPg devopam.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to devopam/MCPg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/devopam/MCPg/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/devopam/MCPg

Made for: Claude Code.

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 MCPg CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/devopam/mcpg/claude-md/github.svg)](https://agentmods.dev/instructions/devopam/mcpg/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/devopam/mcpg/claude-md"><img src="https://agentmods.dev/badge/instructions/devopam/mcpg/claude-md/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.

agentmods 80×15 button for MCPg CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/devopam/mcpg/claude-md"><img src="https://agentmods.dev/badge/instructions/devopam/mcpg/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,559 This file is loaded in full into every session.
When invoked 1,559 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01559 $0.01559
Opus 5.5 $0.00624 $0.00624
Sonnet 5.5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured today against content hash 0e036b118e7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCPg 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 today.

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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MCPg project memory

Durable facts and conventions for working in this repo. Kept short so it stays true; verify anything here against the code before relying on it.

What MCPg is

A production-grade PostgreSQL MCP server. Single-process, async (asyncio), Python 3.12–3.14. 279 MCP tools (read-only mode exposes a subset). Ships to PyPI (mcpg), GHCR, the MCP registry, Smithery, and a read-only HF Spaces demo.

Golden rules

  • Verify before you write — especially docs. Every claim in a doc must be checked against the code, the CLI, or a live endpoint, never from memory. This is a hard project rule.
  • Generated beats hand-maintained. If a catalogue can drift, it's generated and guarded by a test. Don't hand-edit generated blocks.
  • Commit per logical slice, push often. Big multi-batch changes have been lost to context resets — small commits survive.
  • Never hand-edit src/mcpg/_vendor/ (see below).

Source-of-truth map (don't duplicate these — point at them)

  • Version: src/mcpg/__init__.py __version__. pyproject.toml reads it dynamically via hatchling (dynamic = ["version"]). The MCPB bundle pins are synced by packaging/mcpb/sync_version.py; tests/unit/test_mcpb_bundle.py enforces the match. The Cursor plugin version in .cursor-plugin/plugin.json and the uvx [email protected] pin in packaging/cursor/mcp.json are synced by packaging/cursor/sync_plugin_version.py (tests/unit/test_cursor_plugin.py). A release bumps exactly one line, then runs the sync scripts.
  • Tool surface: tests/contract/tool_surface.snapshot.json (281 tools) is the contract. about.py's tool_count = len(tool_names). Two contract snapshots (surface + return shapes) — regenerate with MCPG_REGENERATE_TOOL_SNAPSHOT=1 / MCPG_REGENERATE_TOOL_RETURN_SHAPES=1 and commit the diffs.
  • Doc reference tables: the tool index (docs/tools.md) and module map (docs/architecture.md) are generated by tools/generate_doc_tables.py and guarded by tests/contract/test_doc_tables.py. Regenerate and paste between the <!-- BEGIN/END generated --> markers; don't hand-edit.
  • Access modes: src/mcpg/policy.py. read-only (reads) / restricted (reads + DML writes — the "safe read-write" tier) / unrestricted (everything). DDL / SHELL / LISTEN (and MIGRATE, which piggybacks on DDL) each additionally need MCPG_ALLOW_* in unrestricted mode.
  • NL→SQL providers: 19 built-in via the _PROVIDERS registry in src/mcpg/nl2sql.py (single source; deviating key env vars: HF_TOKEN, GITHUB_TOKEN, DEEPINFRA_TOKEN). The provider table in docs/user-guide.md mirrors it.

Read the full file on GitHub · 108 lines

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. today Changed · +3 lines · +68 tokens per session 0e036b118e7d
  2. 14d ago Changed 7326f70a49fe
  3. 21d ago Changed · +11 lines · +196 tokens per session b85f5306cedb
  4. 1mo ago First seen · 94 lines · 1,295 tokens per session scan A c951a42f7cc4

Subscribe to this mod's changes

MCPg CLAUDE.md is an instructions file published in the GitHub repository devopam/MCPg (14 stars, last pushed yesterday), licensed MIT. It adds 1,559 tokens to every session, about $0.0062 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.

Claude CodeDatabasesPostgreSQLaianthropicclaudedatabase-tools
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens