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.
git clone --depth 1 https://github.com/kms9/ggb-web-mcpWrote 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.
[](https://agentmods.dev/rules/kms9/ggb-web-mcp/prd)<a href="https://agentmods.dev/rules/kms9/ggb-web-mcp/prd"><img src="https://agentmods.dev/badge/rules/kms9/ggb-web-mcp/prd/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.
<a href="https://agentmods.dev/rules/kms9/ggb-web-mcp/prd"><img src="https://agentmods.dev/badge/rules/kms9/ggb-web-mcp/prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.02007 | $0.02007 |
| Opus 5.5 | $0.00803 | $0.00803 |
| Sonnet 5.5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
prd 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Requirements Document: GeoGebra MCP Tool
Product Overview
The GeoGebra MCP Tool is a Model Context Protocol server that enables AI models to interact with GeoGebra's mathematical software suite. This tool allows AI assistants to create, manipulate, and analyze mathematical constructions, graphs, and geometric objects through GeoGebra's comprehensive API, bringing dynamic mathematical visualization capabilities directly into AI conversations[1][2].
Problem Statement
Current AI models excel at mathematical reasoning and problem-solving but lack the ability to create interactive mathematical visualizations and dynamic constructions. Students, educators, and researchers need AI assistants that can not only solve mathematical problems but also generate visual representations, interactive graphs, and geometric constructions that enhance understanding and exploration of mathematical concepts.
Target Users
Primary Users:
- Mathematics Educators: Teachers who want AI assistance in creating interactive lessons and visual demonstrations
- Students: Learners who need AI help with mathematical problem-solving that includes visual components
- Researchers: Academics requiring dynamic mathematical modeling and visualization
Secondary Users:
- Educational Content Creators: Developers building AI-powered educational platforms
- Tutoring Applications: AI tutoring systems that need mathematical visualization capabilities
Product Goals
Primary Objectives
- Enable AI models to create and manipulate GeoGebra constructions programmatically
- Provide seamless integration between natural language mathematical requests and visual outputs
- Support real-time mathematical exploration and hypothesis testing through AI
Success Metrics
- Adoption Rate: 1,000+ active MCP server instances within 6 months
- User Engagement: Average of 50+ tool calls per active user per month
- Educational Impact: 80% of educator users report improved student engagement
- Technical Performance: <2 second response time for construction creation
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.
- 1mo ago First seen · 185 lines · 2,007 tokens per session scan A b350477aaa73
prd is a cursor rule published in the GitHub repository kms9/ggb-web-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 2,007 tokens to every session, about $0.0080 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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.