pypowsybl-mcp: Instructions file for Codex

AGENTS.md

pypowsybl-mcp AGENTS.md is an instructions file for Codex, OpenCode from powsybl/pypowsybl-mcp. It costs 606 tokens per session, scanned A, original, MPL-2.0.

Coding instructions for pypowsybl-mcp, a project connecting MCP servers to pypowsybl for power-grid operations.

In plain words
What is it for?
They guide changes to the Python project, including dependency setup with uv, logging with loguru, linting with ruff, documentation updates, and pytest tests.
Why use it?
They keep contributions consistent by defining project structure, dependency management, logging, language style, documentation, formatting, and testing rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is powsybl/pypowsybl-mcp's own configuration. It tells Codex and OpenCode how to work on pypowsybl-mcp 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 pypowsybl-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to powsybl/pypowsybl-mcp. 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/powsybl/pypowsybl-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/powsybl/pypowsybl-mcp

Made for: Codex, OpenCode.

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 pypowsybl-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/powsybl/pypowsybl-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/powsybl/pypowsybl-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/powsybl/pypowsybl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/powsybl/pypowsybl-mcp/agents-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 pypowsybl-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/powsybl/pypowsybl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/powsybl/pypowsybl-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 606 This file is loaded in full into every session.
When invoked 606 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 $0.00606 $0.00606
Opus 5.5 $0.00242 $0.00242
Sonnet 5.5 $0.00121 $0.00121
Haiku 4.5 $0.00061 $0.00061

Measured 1mo ago against content hash 755c3b876c7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pypowsybl-mcp AGENTS.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 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.

AGENTS.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Agent Guidelines

Project Overview

pypowsybl-mcp is a project that integrates MCP (Model Context Protocol) servers for power grid operations, specifically using pypowsybl.

Development Rules

  • Follow existing code style (indentation, naming conventions).
  • Maintain documentation: README.md with new major features and update the docs directory if needed.
  • Use uv for dependency management.
  • Use loguru for logging.
  • ruff is used for linting and formatting.
  • Write code and comments in English.
  • Use American English spelling (e.g. "color", "initialize", "catalog") in README.md, code comments, and the docs/ directory.

Git Workflow

  • Never push. Do not run git push (nor git push --force, nor push tags) under any circumstance. Committing locally is fine; publishing is the maintainer's decision.
  • Never open a pull request. Do not run gh pr create or otherwise open, edit, or merge a pull request. Leave the work on a local branch and report what is ready.
  • One single line per commit message. A commit message is exactly one line — a short, imperative description of the change — followed by the human author's Signed-off-by: trailer. Nothing else: no body, no bullet list, no Co-authored-by: trailer.
  • Never mention the LLM. No reference of any kind to the model, agent, or assistant that co-authored the code — not in the commit message, not in trailers, not in code comments, not in documentation.
  • Branch naming convention. Create a branch for the change (never commit directly on main) and prefix its name with the type of work, followed by a short kebab-case description:
    • feat/ — new feature (e.g. feat/creation-tools)
    • fix/ — bug fix (e.g. fix/per-unit-comparison)
    • refactor/ — restructuring with no behavior change
    • docs/ — documentation only
    • test/ — tests only
    • chore/ — tooling, dependencies, CI
  • Never commit real secrets in .env/.env.* files. When adding a new environment variable, document it (with a comment) in .env.template rather than only setting it locally.

Read the full file on GitHub · 52 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. 1mo ago Changed · +22 lines · +377 tokens per session 755c3b876c7a
  2. 2mo ago First seen · 30 lines · 229 tokens per session scan A dba3ab88cf6a

Subscribe to this mod's changes

pypowsybl-mcp AGENTS.md is an instructions file published in the GitHub repository powsybl/pypowsybl-mcp (7 stars, last pushed today), licensed MPL-2.0. It adds 606 tokens to every session, about $0.0024 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.

Related

pypowsybl-mcp AGENTS.md compared with instructions from other repositories

pypowsybl-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pypowsybl-mcp AGENTS.mdpowsybl/pypowsybl-mcpInstructions file7todayMPL-2.0A606Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode