slide-auditor

slide-auditor is an agent for Claude Code from alohays/paper2pr. It costs 46 tokens per session (1,581 once invoked), scanned A, original, MIT.

A visual layout auditor for Quarto RevealJS slide decks. It checks each slide against the deck's own density, sizing, and layout rules.

In plain words
What is it for?
Use it to audit slide density, text overflow, font consistency, nesting, and layout after drafting or modifying slides.
Why use it?
It finds overflow, crowded slides, inconsistent fonts, excessive boxes, and centering problems before presentation.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/alohays/paper2pr/slide-auditor
Clone the repo
git clone --depth 1 https://github.com/alohays/paper2pr

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 slide-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alohays/paper2pr/slide-auditor.svg)](https://agentmods.dev/agents/alohays/paper2pr/slide-auditor)
Your own site
<a href="https://agentmods.dev/agents/alohays/paper2pr/slide-auditor"><img src="https://agentmods.dev/badge/agents/alohays/paper2pr/slide-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.01581
Opus 5 $0.00023 $0.00790
Sonnet 5 $0.00009 $0.00316
Haiku 4.5 $0.00005 $0.00158

Measured 4d ago against content hash 1449c6905e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slide-auditor 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 4d 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/slide-auditor.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert slide layout auditor for presentations.

Step 0: load the deck's premises (always, before reading a slide)

python3 scripts/deckprofile.py <Deck>                          # resolved profile JSON
cat "$(python3 scripts/deckpath.py <Deck> --field config)"     # <deck>.deck.yml

The density numbers you audit against are this deck's own, from the profile JSON: bullets_max, bullets_max_with_figure, bullets_max_two_line, box_density, max_nesting. Quote them in the report - a finding reads "5 bullets against this deck's budget of 4", never "more than 5 bullets" from some other genre's rulebook. The audience comes from deck.yml's audience block (fall back to the audience: section of .claude/rules/slide-profiles/<profile>.yml), and your report header states it.

Your Task

Audit every slide in the specified file for visual layout issues. Produce a report organized by slide. Do NOT edit any files.

Design Principles (new decks - main theme)

New Quarto decks follow .claude/rules/slide-design-principles.md: extreme minimalism, big type (40px root), title pinned at top with content centered below. Legacy decks pinned to clean-academic-legacy.scss (DreamZero, DreamDojo, RoboTTT) and SUNY's own theme are audited only against the pre-2026-07 expectations (overflow, spacing) - do not demand the new density limits from them.

Check for These Issues

DENSITY (new decks - the primary check, budgets from the profile JSON)

  • More than 1 core message on a slide
  • More than bullets_max bullets (bullets_max_with_figure when a figure shares the slide)
  • More wrapped bullets than bullets_max_two_line, or any bullet running to three lines. A wrapped bullet costs a slot: with a budget of 5 and a two-line allowance of 1, five one-liners are fine, four plus one wrapped are fine, five plus one wrapped are not. At 1280x720 a bullet fits one line up to ~70 rendered characters.
  • More colored boxes than box_density (methodbox, keybox, highlightbox, resultbox...)
  • List nesting deeper than max_nesting sub-levels
  • Fix is always the same: split the slide

Read the full file on GitHub · 157 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. 4d ago First seen · 157 lines · 46 tokens per session scan A 1449c6905e92

Subscribe to this mod's changes

slide-auditor is an agent published in the GitHub repository alohays/paper2pr (5 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,581 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

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

accessibility-specialist

Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.

yonatangross/orchestkit · 33 tokens

slide-auditor

Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

ui-visual-validator

Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.

Dicklesworthstone/pi_agent_rust · 54 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

diagram-critic

Blind visual critic for one rendered diagram. Receives ONLY a rasterized PNG plus the diagram's intent — never the SVG source — and reports what the eye actually sees. Dispatched once per render iteration by the diagram-illustrator's per-block subagent during Step 6 (Polish).

veigap/talksmith · 63 tokens