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.
npx skills add YZDame/geogebra-mcp-server --skill geogebra-setupgit clone --depth 1 https://github.com/YZDame/geogebra-mcp-serverWrote 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/skills/yzdame/geogebra-mcp-server/geogebra-setup)<a href="https://agentmods.dev/skills/yzdame/geogebra-mcp-server/geogebra-setup"><img src="https://agentmods.dev/badge/skills/yzdame/geogebra-mcp-server/geogebra-setup/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/skills/yzdame/geogebra-mcp-server/geogebra-setup"><img src="https://agentmods.dev/badge/skills/yzdame/geogebra-mcp-server/geogebra-setup.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 | $0.00035 | $0.00387 |
| Opus 5.5 | $0.00014 | $0.00155 |
| Sonnet 5.5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
geogebra-setup 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 6d 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.
What it actually says
Locate this plugin's root from the current skill path. Check Node >=22.12.0,
package.json, and dist/cli.js. In a source checkout run npm ci then
npm run build. The bundled MCP configuration runs node ./dist/cli.js with
cwd set to the plugin root. For a client that does not resolve plugin-relative
working directories, configure the absolute CLI path explicitly.
Use server_info and geogebra_instance_status to inspect connection and engine
state. HTML generation works without Chromium. For server-side rendering, install
Puppeteer's browser with npx puppeteer browsers install chrome or set
PUPPETEER_EXECUTABLE_PATH to an existing compatible Chrome executable. Check
network access to GeoGebra if loading fails. Do not report mock results as live exports.
Gikz is optional: configure GIKZ_CLI with an absolute path to its separately
installed gikz.js. Keep GPL notices with that installation. Do not auto-download
or execute a replacement CLI merely because an export reports it missing.
pdflatex, asy, and tsqx are optional source-verification tools; their absence
does not prevent native GGB/PNG/SVG/PDF exports. Do not overwrite the user's MCP
configuration or publish a server as part of setup unless requested.
The bundled Streamable HTTP mode binds only to loopback and shares one workspace construction. Public ChatGPT connections need a separately deployed HTTPS endpoint and appropriate authentication/isolation. Installing a local plugin does not publish it to a directory or verify ChatGPT UI compatibility.
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.
- 6d ago First seen · 30 lines · 35 tokens per session scan A 63c16beddbd2
geogebra-setup is a skill published in the GitHub repository YZDame/geogebra-mcp-server (2 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 387 once invoked, about $0.0001 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 2026-10-11.
Other skills, from other repositories
mathgraphs
Math graphing, 3D scene building with lights and particles, and presentations.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
build-interactive-explainers
A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
tooluniverse-nfcore-pipelines
Run real end-to-end bioinformatics pipelines (nf-core rnaseq, sarek, atacseq) via Nextflow + Docker/Singularity, for raw FASTQ/BAM data — either local files or public GEO/SRA datasets. Use when someone asks to "run RNA-seq alignment", "quantify gene expression from FASTQs", "call germline or somatic variants from my…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…