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 LuuOW/meridian-mcp --skill latexgit clone --depth 1 https://github.com/LuuOW/meridian-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/skills/luuow/meridian-mcp/latex)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/latex"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/latex/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/luuow/meridian-mcp/latex"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/latex.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 | $0.00050 | $0.01428 |
| Opus 5 | $0.00025 | $0.00714 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
latex 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
latex
Production mathematical typesetting for arXiv preprints, academic papers, and web-rendered equations. Covers the full pipeline from mathematical intuition → LaTeX notation → rendered output, for both document (PDFLaTeX/XeTeX) and web (KaTeX/MathJax) targets.
Core Math Environments
% Inline math — use sparingly, only for simple symbols in prose
The energy $E = mc^2$ follows from special relativity.
% Display math — numbered equation
\begin{equation}
\mathcal{L} = \bar{\psi}(i\gamma^\mu \partial_\mu - m)\psi
\label{eq:dirac}
\end{equation}
% Unnumbered display
\[
\hat{H}\psi = E\psi
\]
% Multi-line aligned (align not eqnarray)
\begin{align}
\nabla \cdot \mathbf{E} &= \frac{\rho}{\varepsilon_0} \\
\nabla \times \mathbf{B} &= \mu_0 \mathbf{J} + \mu_0\varepsilon_0 \frac{\partial \mathbf{E}}{\partial t}
\label{eq:maxwell}
\end{align}
Common Physics Notation
% Quantum operators
\hat{a},\, \hat{a}^\dagger % annihilation / creation
\langle \psi | \hat{O} | \phi \rangle % Dirac bracket
\hbar\omega % reduced Planck × frequency
% Statistical mechanics
Z = \mathrm{Tr}\left[e^{-\beta \hat{H}}\right]
\langle O \rangle = -\frac{\partial \ln Z}{\partial \lambda}
% General relativity
g_{\mu\nu},\quad R_{\mu\nu} - \tfrac{1}{2}g_{\mu\nu}R + \Lambda g_{\mu\nu} = \frac{8\pi G}{c^4}T_{\mu\nu}
% Information / entropy
S = -\sum_i p_i \ln p_i
\mathcal{I}(\rho) = S(\rho \| \sigma) = \mathrm{Tr}[\rho(\ln\rho - \ln\sigma)]
KaTeX Web Rendering
KaTeX is the correct choice for web — faster than MathJax, same quality for standard notation.
// Lazy-load — only when math detected
let _katex = null
async function renderMath(container) {
const spans = container.querySelectorAll('.math-block, .math-inline')
if (!spans.length) return
if (!_katex) _katex = (await import('https://esm.sh/[email protected]')).default
spans.forEach(el => {
el.innerHTML = _katex.renderToString(el.dataset.formula, {
displayMode: el.classList.contains('math-block'),
throwOnError: false,
})
})
}
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.
- 10d ago First seen · 145 lines · 50 tokens per session scan A 774facb09321
latex is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,428 once invoked, about $0.0003 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.
Other skills, from other repositories
latex-econ-model
Write and typeset economic models in LaTeX with proper notation.
template-search-project
Literature-search pipeline exemplar — multi-backend search (arXiv/Crossref), BibTeX generation, deep search, optional LLM synthesis.
latex-econ-model
Write and typeset economic models in LaTeX with proper notation.
academic-figure
A Chinese-language toolkit for making and checking academic charts, diagrams, flowcharts, and graphical abstracts. A graphical abstract is a visual summary of a research paper, while a flowchart shows the steps or decisions in a process.
academic-response
A workflow for preparing replies to academic peer reviewers, meaning researchers who evaluate a paper before publication. It classifies their comments, maps each comment to an action, drafts point-by-point replies, and checks the final response.
academic-writing
A Chinese academic writing assistant for turning drafts, informal notes, or data into formal research-paper text. It also handles translation, editing, checks, peer-review simulation, and analysis of results.