math

math is a skill for Claude Code from danielsimonjr/math-mcp. It costs 205 tokens per session (2,068 once invoked), scanned A, original, ISC.

A playbook for using seven mathematical tools through the `math-mcp` server. It covers calculations, calculus, equations, simplification, matrices, statistics, and unit conversion, and explains which tool to use.

In plain words
What is it for?
Use it for exact calculations, derivatives, equation solving, matrix operations, statistical work, and converting units.
Why use it?
It helps the assistant choose the right calculation tool and reduces errors from doing non-trivial maths by hand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the math-mcp plugin — 1 skill, 1 MCP server shipped together

Good fit Use it for exact calculations, derivatives, equation solving, matrix operations, statistical work, and converting units.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielsimonjr/math-mcp/math
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.

Any agent
npx skills add danielsimonjr/math-mcp --skill math
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/math-mcp

Made for: Claude Code.

Or install math-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 math

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielsimonjr/math-mcp/math/github.svg)](https://agentmods.dev/skills/danielsimonjr/math-mcp/math)
Your own site
<a href="https://agentmods.dev/skills/danielsimonjr/math-mcp/math"><img src="https://agentmods.dev/badge/skills/danielsimonjr/math-mcp/math/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.

agentmods 80×15 button for math

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielsimonjr/math-mcp/math"><img src="https://agentmods.dev/badge/skills/danielsimonjr/math-mcp/math.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00205 $0.02068
Opus 5.5 $0.00082 $0.00827
Sonnet 5.5 $0.00041 $0.00414
Haiku 4.5 $0.00020 $0.00207

Measured 2mo ago against content hash 8c6386647af2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

plugin/skills/math/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Math

A judgment layer over the math-mcp server's 7 pure computation tools — expression evaluation, calculus, equation solving, simplification, matrix algebra, statistics, and unit conversion. This skill adds no tools of its own: every action below is one of the server's existing MCP tools. Its job is to steer you toward calling the tool instead of computing in your head, help you pick evaluate vs. a specialized tool, sequence multi-step workflows correctly, and flag the mathjs-compatible-syntax gotchas that produce wrong or confusing results. The compute engine is MathTS (@danielsimonjr/mathts-*), which keeps mathjs-compatible input syntax.

Skill root: this skill ships inside the math-mcp plugin (repo danielsimonjr/math-mcp, skills/math/). Slash trigger: /math.

The offload rule

Non-trivial computation goes to math-mcp, not mental math. Self-computed arithmetic is error-prone — the moment a calculation is worth getting exactly right, call the tool instead of estimating or working it out by hand. This is the same principle as "prefer the MCP over ad-hoc work" from the windows skill, applied to numbers instead of the desktop.

Where the line sits:

  • Trivial inline arithmetic — 2+2, a single-digit product, a fact you already know cold — may be answered directly.
  • Everything else goes to the tool: exact/CAS results, any derivative or calculus step, any matrix operation beyond a hand-checkable 2×2, statistics over a real dataset, unit conversions, and any figure the user will actually rely on (a report number, a formula check, an engineering value). If it's worth being right about, it's worth calling the tool.

Tool selection: evaluate vs. the 6 specialized tools

The overlap between evaluate and the specialized tools is intentional. evaluate is the MathTS workhorse (mathjs-compatible syntax) — it can inline derivative(...), det(...), and most of what the specialized tools do, all in one expression. Use evaluate for a one-off general expression or when combining several operations in a single call (pass a scope object to supply variables). Reach for a specialized tool when you want its narrower, validated result shape or its specific operation directly — e.g. a clean symbolic derivative string from derivative, or an enum-constrained matrix op from matrix_operations.

Read the full file on GitHub · 92 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 92 lines · 205 tokens per session scan A 8c6386647af2

Subscribe to this mod's changes

math is a skill published in the GitHub repository danielsimonjr/math-mcp (0 stars, last pushed 21d ago), licensed ISC. It adds 205 tokens to every session and 2,068 once invoked, about $0.0008 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 2026-09-01.

Related

math compared with skills from other repositories

math next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mathdanielsimonjr/math-mcpSkill021d agoISCA205Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill36k2d agoApache-2.0A123Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill57k7d agoMITA83Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill57k7d agoMITA44Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill57k7d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill34ktodayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8ktodayApache-2.0A205Claude Code