agentmods.dev

Geogebra_mcp AGENTS.md

Geogebra_mcp AGENTS.md is an instructions file for Codex, OpenCode from 123pc/Geogebra_mcp. It costs 580 tokens per session, scanned A, original, MIT.

Project instructions for setting up and using GeoGebra MCP with AI coding agents. GeoGebra is software for interactive mathematics, including geometry drawings.

In plain words
What is it for?
They guide configuration for Claude Code or Codex, installation troubleshooting, status checks, triangle drawing, and later GeoGebra diagnostics.
Why use it?
They provide a defined setup and verification process so the agent configures the right tools and confirms that GeoGebra works.

Instructions file for CodexOpenCode

not rated 4 3mo ago A scan 580 tokens original MIT
View the source file 123pc/Geogebra_mcp
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/123pc/geogebra_mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/123pc/Geogebra_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 Geogebra_mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/123pc/geogebra_mcp/agents-md.svg)](https://agentmods.dev/instructions/123pc/geogebra_mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/123pc/geogebra_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/123pc/geogebra_mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 580 This file is loaded in full into every session.
When invoked 580 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 $0.00580 $0.00580
Opus 5 $0.00290 $0.00290
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 3d ago against content hash 670fc596ab91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Geogebra_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 3d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GeoGebra MCP Agent Guide

This repository supports natural-language setup by AI coding agents.

When the user asks for any of the following:

  • "Set up GeoGebra MCP"
  • "Install GeoGebra MCP"
  • "Configure this project for Claude Code/Codex"
  • "按照项目说明自动安装 GeoGebra MCP"

follow this workflow:

  1. Read skills/geogebra-setup/SKILL.md.

  2. Ask the user which AI agent(s) to configure (Claude Code, Codex, or both) before running the setup script. Wait for their response.

  3. Run the setup script from the repository root with the appropriate --agent flag:

    python scripts/setup_geogebra_mcp.py --agent <choice>

    Where <choice> is claude, codex, or all based on the user's answer.

  4. If dependency installation is blocked by permissions or network restrictions, ask the user to approve the command and rerun it.

  5. After setup, ask the user to restart their agent session.

  6. In the new session, verify with:

    Use GeoGebra MCP to check status and draw a triangle.

For drawing and troubleshooting after installation, use:

  • skills/use-geogebra-mcp/SKILL.md for MCP usage and diagnostics.
  • skills/geogebra-master/SKILL.md for expert GeoGebra construction strategy.

Skill Development Guidelines

When modifying skill files, follow these checks before committing to prevent test-set pollution:

  1. Eliminate construction-type-specific residue. Search skill files for content that overfits to one type of drawing task — e.g., hardcoded mechanism parameters (such as crank-rocker's O1=(0,0), O2=(6,0), link lengths 5 and 4), specific slider speeds, or workflows that only apply to one construction type. Example patterns in skills (such as mechanism templates) should serve as references, not the only path. Ensure the skill works equally well for function graphs, plane geometry, 3D graphics, data charts, and mechanism animations.

  2. Verify with a different construction type. After modifying a skill, test it with at least one drawing task of a different type than the one used for debugging. For example, if you tuned the skill using four-bar linkage tasks, also test a function graph or 3D graphics task to confirm the modification did not break other construction workflows.

Read the full file on GitHub · 46 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. 3d ago First seen · 46 lines · 580 tokens per session scan A 670fc596ab91

Subscribe to this mod's changes

Geogebra_mcp AGENTS.md is an instructions file published in the GitHub repository 123pc/Geogebra_mcp (4 stars, last pushed 3mo ago), licensed MIT. It adds 580 tokens to every session, about $0.0029 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.

Learning and teachingclaude-code-mcpcodex-mcpgeogebramcp
Related

Other instructions, from other repositories

geogebra-mcp-server AGENTS.md

Instructions for YZDame/geogebra-mcp-server, covering agents.md, project context, code map, development rules and tool implementation checklist.

YZDame/geogebra-mcp-server · 438 tokens

Tutorial_AwesomeModernCPP AGENTS.md

AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).

Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP · 778 tokens

open-dictionary AGENTS.md

Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.

ahpxex/open-dictionary · 1,906 tokens

ab900 CLAUDE.md

Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.

timothywarner-org/ab900 · 7,662 tokens

canvas-lms-mcp AGENTS.md

Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.

bruchris/canvas-lms-mcp · 1,800 tokens

obsidian-university-workflow CLAUDE.md

Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.

ABO896/obsidian-university-workflow · 810 tokens