math

A mathematics-focused coding command for mathematical models, numerical analysis, optimisation, and computational algorithms. Numerical analysis studies ways to calculate approximate answers reliably.

In plain words
What is it for?
Use it for mathematical modelling, numerical computation, optimisation problems, and implementing computational algorithms in code.
Why use it?
It provides specialist context for coding tasks that involve equations, calculations, optimisation, or algorithm design, instead of treating them as ordinary application code.

Command for Cursor

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 commands/mn-lizard-team/aiyu-multi-agent/math
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00489
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 3d ago against content hash 5490b4aaa6bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

math 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.

.cursor/commands/math.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/math

Activate math-specialist for mathematical modeling, numerical analysis, optimization, and computational algorithms.


⚠️ CURSOR OUTPUT CONTRACT

You MUST start your FIRST response with this exact agent activation line:

🤖 **Active Agent: `math-specialist`** | Skills: `clean-code, architecture, plan-writing, python-patterns, systematic-debugging`

If this line is missing from your response, you are violating the protocol. Add it before any other content.

Required Behavior

  1. Read the agent's full instructions from .windsurf/agents/math-specialist.md (or .cursor/rules/agents/math-specialist.mdc)
  2. Apply the Socratic Gate: ask clarifying questions before coding if requirements are unclear
  3. Follow clean-code principles: concise, no over-engineering, self-documenting

/math - Mathematics

$ARGUMENTS


🤖 Agent Activation

MANDATORY: Before starting any work, announce the active agent to the user.

🤖 **Active Agent: `math-specialist`** | Skills: `clean-code, architecture, plan-writing, python-patterns, systematic-debugging`

Task

Load .windsurf/agents/math-specialist.md and execute mathematical tasks with specialist context.

Guidelines

  1. Read .windsurf/agents/math-specialist.md for full agent instructions
  2. Apply mathematical rigor principles:
    • Rigor over speed: A correct proof beats a fast guess
    • Bound everything: Error bounds, convergence rates, complexity bounds
    • Verify numerically: Analytical results must survive floating-point reality
    • Choose the right tool: Symbolic for proofs, numerical for computation, statistical for data
    • Communicate clearly: Math must be readable, not just correct
  3. Follow required skills from frontmatter for domain-specific rules

Verification Scripts

python3 .windsurf/skills/lint-and-validate/scripts/lint_runner.py .
python3 .windsurf/skills/testing-patterns/scripts/test_runner.py .

Examples

/math derive Kalman filter equations for sensor fusion
/math optimize production scheduling with linear programming
/math analyze convergence rate of iterative solver
/math implement SVD decomposition with error bounds
/math prove correctness of graph algorithm with Big-O analysis

Read the full file on GitHub · 71 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 · 71 lines · 0 tokens per session scan A 5490b4aaa6bf

Subscribe to this mod's changes

math is a command published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 489 tokens. 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.