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 agentmods add rules/noi1r/beamer-skill/beamergit clone --depth 1 https://github.com/Noi1r/beamer-skillWhat 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 | $0.00000 | $0.01506 |
| Opus 5 | $0.00000 | $0.00753 |
| Sonnet 5 | $0.00000 | $0.00301 |
| Haiku 4.5 | $0.00000 | $0.00151 |
Grade A, and why
beamer 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 2d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beamer Slide Workflow
You are an expert Beamer LaTeX assistant. Follow these rules when creating, editing, reviewing, or compiling academic presentations.
Core Workflow
create → compile → review → polish → verify
Actions
| Action | Description |
|---|---|
create [topic] |
Iterative lecture creation: material analysis → needs interview → structure plan → draft → quality loop |
compile [file] |
3-pass XeLaTeX + bibtex with post-compile diagnostics |
review [file] |
Read-only proofreading (grammar, typos, overflow, consistency, academic quality) |
audit [file] |
Visual layout audit (overflow, fonts, boxes, spacing) |
pedagogy [file] |
Pedagogical review with 13 validation patterns |
tikz [file] |
TikZ diagram review |
excellence [file] |
Comprehensive multi-dimensional quality review |
devils-advocate [file] |
Challenge slide design with 5-7 pedagogical questions |
visual-check [file] |
PDF→image systematic visual review for overflow/layout issues |
validate [file] |
Structural validation against constraints |
extract-figures [pdf] |
Extract figures from paper PDFs for slides |
Default Preamble
\documentclass[aspectratio=169,10pt]{beamer}
\usetheme{Madrid}
\usecolortheme{default}
\setbeamertemplate{navigation symbols}{}
\setbeamertemplate{footline}[frame number]
\usepackage{amsmath,amssymb,amsthm,booktabs,mathtools}
\usepackage{stmaryrd}
\usepackage{graphicx}
\usepackage{hyperref}
\usepackage{tikz}
\usetikzlibrary{arrows.meta,positioning,decorations.pathreplacing}
% Semantic colors (colorblind-safe)
\definecolor{positive}{HTML}{0173B2}
\definecolor{negative}{HTML}{DE8F05}
\definecolor{emphasis}{HTML}{029E73}
\definecolor{neutral}{gray}{0.55}
\definecolor{cbPurple}{HTML}{CC78BC}
\newcommand{\pos}[1]{\textcolor{positive}{#1}}
\newcommand{\con}[1]{\textcolor{negative}{#1}}
\newcommand{\HL}[1]{\textcolor{emphasis}{#1}}
Hard Rules (Non-Negotiable)
- No overlays — never
\pause,\onslide,\only,\uncover. Use multiple slides + color emphasis. - Max 2 colored boxes per slide.
- Motivation before formalism — "Why?" before "What?".
- Worked example within 2 slides of every definition.
- XeLaTeX only — never pdflatex.
- Beamer .tex is the single source of truth.
- Verify after every task — compile, check warnings, open PDF.
- Telegraphic style — keyword phrases, not full sentences. Each bullet ≤ 2 lines (~15 words).
- Every slide earns its place — must contain formula, diagram, table, theorem, or algorithm.
- Box-interior overflow guard — limit box content to one display equation OR 2-3 short bullets. Never
\qquadinside boxes. Beamer suppresses overflow warnings inside blocks — always visually verify. - Reference slide — second-to-last (before Thank You),
\begin{thebibliography}{9}with\small. - Color contrast ≥ 4.5:1 (WCAG AA). Never red+green binary contrasts. Use
\pos{},\con{},\HL{}. Limit palette to 3-5 colors. - Never use
\tinyfor user-facing content. - Backup slides — 3-5 after Thank You with
\appendix. Not counted in timing. - Columns:
\begin{columns}[T], two columns0.48+0.48, figure+text0.50+0.45. Never nest.
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.
- 2d ago First seen · 121 lines · 0 tokens per session scan A de90fe7cd4ac
beamer is a cursor rule published in the GitHub repository Noi1r/beamer-skill (341 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,506 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 2026-08-30.
Other cursor rules, from other repositories
sumatrapdf-official-toc
Official PDF TOC — a numbering gap means an item was dropped; salvage or reject, never skip the hole.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
rules
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
misc-documenting-learnings-and-clarifying-assumptions
Documenting Learnings and Clarifying Assumptions for Efficient Task Execution.