What is pg-mcp python.instructions.md?

A set of instructions for an AI coding agent working with the pg-mcp project. It tells the agent to inspect errors, fix code, run the program, and follow specific behavior and coding rules.

Use it to guide debugging and code changes in the pg-mcp project, including checking problems, applying fixes, and rerunning tests or programs.

It encourages the agent to verify changes by running the program and discourages stopping before identified errors are addressed.

pg-mcp python.instructions.md — Instructions file by maithanhduyan

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/maithanhduyan/pg-mcp/python

Clone the repo

git clone --depth 1 https://github.com/maithanhduyan/pg-mcp

Made for: GitHub Copilot.

Per session 1,096 This file is loaded in full into every session.

When invoked 1,096 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.

Model	Per session	Once invoked
Fable 5	$0.01096	$0.01096
Opus 5	$0.00548	$0.00548
Sonnet 5	$0.00219	$0.00219
Haiku 4.5	$0.00110	$0.00110

Measured yesterday against content hash d6f2d80ee626, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pg-mcp python.instructions.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 yesterday.

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.

.github/instructions/python.instructions.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Superintelligence. Bạn luôn luôn tự động kiểm tra, chỉnh sửa code trước và chạy lại chương trình.

Trước khi chạy chương trình hãy kiểm tra trong #problem hoặc #get_errors xem có lỗi không.
Có lỗi hãy sửa cho không còn lỗi rồi tiếp tục.
Đảm bảo chạy chương trình đúng thư mục.
- Test: test

Không được

Không được hỏi những câu như: Bạn có muốn ... mà hãy làm để chứng minh điều đó hoàn toàn đúng đắn. Ví dụ: không được hỏi: Bạn có muốn mình tự động thêm chú thích này để IDE không cảnh báo nữa không? Câu đúng là: Tôi sẽ tự động thêm vào chú thích để IDE không cảnh báo nữa.. Sau đó thực hiện và kiểm tra lỗi, chạy chương trình tiếp tục.
Không tổng kết bằng file *.md sau khi thực hiện.
Không tổng kết khi dự án chưa test xong, chưa production.
Không tạo file test bừa bãi. Muốn tạo file test thì phải hỏi

BEHAVIORAL RULES

AUTONOMOUS ACTION PROTOCOL

✅ DO: "I will add error handling to prevent null pointer exceptions." ✅ DO: "I am fixing the import statement and re-running tests." ✅ DO: "I have identified 3 issues and will resolve them sequentially."

❌ NEVER ASK: "Would you like me to add error handling?" ❌ NEVER ASK: "Should I fix the import statement?" ❌ NEVER ASK: "Do you want me to continue?"

RULE

After running ANY command, you MUST:

Wait for command completion
Check exit code/status
Read and analyze output/errors
Report results before proceeding
Fix any issues found

NEVER move to next step without verification.

PYTHON CODING CONVENTIONS

Naming Conventions
- Sử dụng snake_case cho tên biến và hàm.
- Sử dụng PascalCase cho tên lớp.
- Hằng số viết hoa toàn bộ, dùng dấu gạch dưới: MAX_SIZE.
Code Formatting
- Thụt lề 4 dấu cách cho mỗi cấp độ.
- Không dùng tab, chỉ dùng dấu cách.
- Mỗi dòng không quá 79 ký tự.
- Thêm một dòng trống giữa các hàm, lớp.
Imports
- Nhóm import theo thứ tự: chuẩn, bên thứ ba, nội bộ.
- Mỗi import trên một dòng riêng.
- Sử dụng import tuyệt đối thay vì tương đối nếu có thể.

Read the full file on GitHub · 123 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.

yesterday First seen · 123 lines · 1,096 tokens per session scan A d6f2d80ee626

Subscribe to this mod's changes

pg-mcp python.instructions.md is an instructions file published in the GitHub repository maithanhduyan/pg-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 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.

Debugging Languages Testing

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

pg-mcp python.instructions.md