agentmods.dev

mathtype-for-word

mathtype-for-word is a skill for Claude Code, Codex from felimet/mathtype-for-word. It costs 123 tokens per session (3,364 once invoked), scanned A, original, MIT.

A tool for creating and managing genuine MathType equations in Microsoft Word documents and PowerPoint presentations. MathType is equation-editing software, and the tool preserves its native numbering and cross-references.

In plain words
What is it for?
Use it to create or replace equations, convert TeX into MathType equations, number equations, add cross-references, and inspect or validate equation fields in DOCX and PPTX files.
Why use it?
It keeps equations, numbering, and references editable and consistent instead of turning them into images, plain text, or unrelated Word equation objects.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the mathtype-for-word plugin — 1 skill, 1 MCP server shipped together

not rated 3repo 1mo ago A scan 123 tokens original MIT

Good fit Use it to create or replace equations, convert TeX into MathType equations, number equations, add cross-references, and inspect or validate equation fields in DOCX and PPTX files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/felimet/mathtype-for-word/mathtype-for-word
View source ↗ felimet/mathtype-for-word
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 felimet/mathtype-for-word --skill mathtype-for-word
Clone the repo
git clone --depth 1 https://github.com/felimet/mathtype-for-word

Made for: Claude Code, Codex.

Or install mathtype-for-word, 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 mathtype-for-word

README.md
[![agentmods](https://agentmods.dev/badge/skills/felimet/mathtype-for-word/mathtype-for-word.svg)](https://agentmods.dev/skills/felimet/mathtype-for-word/mathtype-for-word)
Your own site
<a href="https://agentmods.dev/skills/felimet/mathtype-for-word/mathtype-for-word"><img src="https://agentmods.dev/badge/skills/felimet/mathtype-for-word/mathtype-for-word.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,364 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 $0.00123 $0.03364
Opus 5 $0.00062 $0.01682
Sonnet 5 $0.00025 $0.00673
Haiku 4.5 $0.00012 $0.00336

Measured 7d ago against content hash 38768fc2fd81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mathtype-for-word 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/invoke-bridge.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/mathtype-for-word/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MathType for Word and PowerPoint

Create real MathType equations in DOCX and PPTX, preserving MathType-native Word numbering and references. Treat source Office files as user data: write a new output unless the user explicitly authorizes in-place replacement.

Non-negotiable invariants

  • Equations are Equation.DSMT4 inline OLE objects created by MathType Toggle TeX.
  • Numbered displays use MathType MACROBUTTON MTPlaceRef and SEQ MTEqn fields.
  • References use MTCommand_InsertEqnRef, its MTReference placeholder, and the target number's MTPlaceRef action. A resolved reference is a GOTOBUTTON containing a nested REF to a ZEqnNum... bookmark.
  • The default number format is simple Arabic equation number only: (1), (2), (3), with chapter and section components disabled.
  • Apply numbering to new numbers and the whole processed document. Update fields after edits.
  • Never substitute Word numbered lists, captions, SEQ Equation, OMath, Unicode-only text, images, or manually typed numbers. Use those only as an explicitly accepted, clearly labeled fallback when MathType is unavailable.
  • PowerPoint equations are centered, floating Equation.DSMT4 OLE objects. PowerPoint has no MathType-native equivalent of Word's equation-number/reference fields, so do not imitate them with typed numbers or links.
  • Keep each symbol's mathematical role and font style consistent across display equations, inline math, prose, captions, and definitions.
  • Keep Word, PowerPoint, and MathType automation silent: leave application windows hidden, suppress modal alerts, do not steal focus, and do not automate visible UI with mouse, keyboard, AppActivate, or SendKeys. If a step cannot run silently, stop and report the limitation.

Terminal selection

  • Detect the active terminal and available executables before invoking the bridge.
  • Use PowerShell 7 directly when the active host is pwsh.exe 7 or later.
  • From Bash on Windows, including Git Bash, or from CMD, invoke the same Windows pwsh.exe bridge commands. From WSL Bash, invoke Windows pwsh.exe; Linux pwsh cannot automate Windows Office COM.
  • Never run the bridge inside Windows PowerShell 5.1. If 5.1 is active, switch to Git Bash or CMD and invoke Windows pwsh.exe there.
  • If no supported terminal or no pwsh.exe is available, stop and ask the user to install PowerShell 7 using https://learn.microsoft.com/zh-tw/powershell/scripting/install/microsoft-update-faq?view=powershell-7.6. Do not silently downgrade the workflow.
  • Read installation-matrix.md for cross-shell commands and agent-specific installation paths.

Read the full file on GitHub · 175 lines

Files

What ships with it

10 files 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. 7d ago First seen · 175 lines · 123 tokens per session scan A 38768fc2fd81

Subscribe to this mod's changes

mathtype-for-word is a skill published in the GitHub repository felimet/mathtype-for-word (3 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 3,364 once invoked, about $0.0006 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 2026-08-31.

Claude CodeDocumentsacademic-writingai-agentchatgptclaude-desktopcross-reference
Related

Other skills, from other repositories

endnote-for-word

Find DOI-verified research papers with the Agent's available scholarly-search or web tools; export and import EndNote-compatible RIS into an existing library or a new library cloned from a verified empty template; and insert, format, update, restyle, inspect, or validate genuine EndNote Cite While You Write (CWYW)…

felimet/endnote-for-word · 175 tokens

dcf-model

Build discounted cash flow valuation workbooks in Excel.

NousResearch/hermes-agent · 14 tokens

comps-analysis

Build comparable-company valuation workbooks in Excel.

NousResearch/hermes-agent · 13 tokens

lbo-model

Build leveraged buyout workbooks with IRR/MOIC in Excel.

NousResearch/hermes-agent · 19 tokens

pdf

PDF files: create, read, merge, fill, OCR, edit text.

NousResearch/hermes-agent · 18 tokens

excel-author

Build auditable financial workbooks headless via openpyxl.

NousResearch/hermes-agent · 16 tokens