Borrowing it
Nothing to install: this file belongs to AbhiRawat4841/mathematica-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.
curl -O https://raw.githubusercontent.com/AbhiRawat4841/mathematica-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/AbhiRawat4841/mathematica-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/instructions/abhirawat4841/mathematica-mcp/agents-md)<a href="https://agentmods.dev/instructions/abhirawat4841/mathematica-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abhirawat4841/mathematica-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00533 | $0.00533 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
mathematica-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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mathematica MCP - Agent Instructions
This project has a Mathematica MCP server connected. It gives you direct control of a running Mathematica instance through MCP tools.
Key concept
A "notebook" here means a LIVE WINDOW inside the Mathematica frontend, not a .nb file on disk.
The default lean profile exposes 12 consolidated tools.
Rules
- ALWAYS use MCP tools for Mathematica work.
- NEVER use
wolframscriptCLI, shell commands,mkdir, or manual.nbfile creation. - For notebook files on disk, prefer
read_notebook_file(path)- no kernel needed. Usenotebooks(action="open"/"save"/"export")only when the user explicitly wants a live window or disk output.
Routing (lean profile, default)
| User says | What to do |
|---|---|
| "calculate", "compute", "solve", "evaluate" | evaluate(code) - kernel, result in chat |
| "plot", "show", "in notebook" | evaluate(code, target="notebook") - in the live notebook |
| "new notebook" | notebooks(action="create", title=...) then evaluate(code, target="notebook") |
| "screenshot", "what does it look like" | screenshot(scope="notebook") (or scope="cell" / "expression") |
| "verify", "check derivation" | verify_derivation(steps) |
| something failed / warnings | kernel(action="messages") then guide(topic="errors") |
Default when ambiguous: evaluate(code) (kernel). More guidance on demand: guide(topic="workflow").
Typical workflow
# User: "integrate x^2 in new notebook and plot it"
1. notebooks(action="create", title="Integration") # opens live notebook window
2. evaluate("Integrate[x^2, x]", target="notebook") # writes + evaluates there
3. evaluate("Plot[x^3/3, {x, -2, 2}]", target="notebook")
That's it. No mkdir, no export, no file search.
With
MATHEMATICA_PROFILE=classic, the legacy names apply instead:execute_code(style=...),create_notebook(title=...),screenshot_notebook,get_messages.
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.
- 7d ago First seen · 45 lines · 533 tokens per session scan A 1bb06492ea77
mathematica-mcp AGENTS.md is an instructions file published in the GitHub repository AbhiRawat4841/mathematica-mcp (48 stars, last pushed 2mo ago), licensed MIT. It adds 533 tokens to every session, about $0.0027 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 2026-08-30.
Other instructions, from other repositories
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.
vscode buildNext.instructions.md
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.