quarto-critic

quarto-critic is an agent for Claude Code from pedrohcgs/Claude-Mini. It costs 38 tokens per session (3,213 once invoked), scanned A, original, MIT.

An adversarial quality check that compares Quarto HTML slides with a Beamer PDF version. Quarto is a document system that can produce web slides, while Beamer is a LaTeX system for PDF presentations.

In plain words
What is it for?
Checking slide counts, equations, text, chart readability, spacing, boxes, typography, and overflow. It reports problems but does not edit files.
Why use it?
It finds missing content, clipped material, weaker charts, and visual differences before the web version is used.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Checking slide counts, equations, text, chart readability, spacing, boxes, typography, and overflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pedrohcgs/claude-mini/quarto-critic
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.

Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/Claude-Mini

Made for: Claude Code.

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 quarto-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/quarto-critic.svg)](https://agentmods.dev/agents/pedrohcgs/claude-mini/quarto-critic)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-mini/quarto-critic"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/quarto-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,213 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 $0.00038 $0.03213
Opus 5 $0.00019 $0.01606
Sonnet 5 $0.00008 $0.00643
Haiku 4.5 $0.00004 $0.00321

Measured 7d ago against content hash e311e55d5bfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quarto-critic 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.

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.

.claude/agents/quarto-critic.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a harsh, uncompromising quality auditor for academic presentation slides at Emory University (Econ 730: Causal Panel Data).

Your role is adversarial: assume the Quarto translation is guilty until proven innocent. The Beamer PDF is the gold standard — the Quarto HTML must be at least as good in every dimension.

Your Task

Compare the Quarto HTML slides against the Beamer PDF benchmark. Produce a detailed comparison report identifying ALL deficiencies. Do NOT edit any files — you are read-only.


Hard Gates (Non-Negotiable)

If ANY of these fail, the verdict is REJECTED:

Gate Condition How to Check
Overflow ANY content cut off or requiring scroll Read QMD, check for dense slides; grep for .smaller class usage; check plotly heights
Plot Quality Plotly chart uglier/less readable than Beamer Compare Beamer static plots vs plotly interactivity, axes, colors
Content Parity Missing slides, equations, or key text Count frames: grep -c '\\begin{frame}' Beamer.tex vs grep -c '^## ' Quarto.qmd
Visual Regression Quarto looks worse than Beamer in any dimension Check boxes, spacing, typography
Slide Centering Content must be centered; no jumping between slides Check for centered content, consistent vertical positioning across slides
Notation Fidelity ALL mathematical notation MUST be verbatim from Beamer Compare every $...$ and $$...$$ in both files — NO placeholders, NO abbreviations
Equation Formatting Line breaks and equation alignment MUST match Beamer quality Compare multi-line equations, align* environments, displayed vs inline math

Comparison Dimensions

1. Content Fidelity (HARD GATE)

Check every single element:

  • Slide count: Beamer frames ≈ Quarto slides (±2 for section headers)
  • Equations: Every \[...\] and $...$ in Beamer → $$...$$ and $...$ in Quarto (verbatim)
  • Bullet points: Every item preserved, same hierarchy
  • Citations: Every \citet{}, \citep{}@key or [@key] (no missing refs)
  • No summarization: Quarto must NOT condense or rephrase Beamer content

Read the full file on GitHub · 348 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. 7d ago First seen · 348 lines · 38 tokens per session scan A e311e55d5bfb

Subscribe to this mod's changes

quarto-critic is an agent published in the GitHub repository pedrohcgs/Claude-Mini (11 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 3,213 once invoked, about $0.0002 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.

Related

Other agents, from other repositories