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 skills/alohays/paper2pr/visual-auditnpx skills add alohays/paper2pr --skill visual-auditgit clone --depth 1 https://github.com/alohays/paper2prWrote 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/alohays/paper2pr/visual-audit)<a href="https://agentmods.dev/skills/alohays/paper2pr/visual-audit"><img src="https://agentmods.dev/badge/skills/alohays/paper2pr/visual-audit.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00857 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
visual-audit 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Audit of Slide Deck
Perform a thorough visual layout audit of a slide deck, on the source and on the rendered pixels.
Steps
-
Resolve the deck named in
$ARGUMENTSand load its premises:python3 scripts/deckpath.py $ARGUMENTS --field qmd # the source python3 scripts/deckprofile.py $ARGUMENTS # resolved profile JSON cat "$(python3 scripts/deckpath.py $ARGUMENTS --field config)" # <deck>.deck.ymlThe density numbers below come from the profile JSON (
bullets_max,bullets_max_with_figure,bullets_max_two_line,box_density,max_nesting); quote the deck's own budget in every density finding. -
Determine the ruleset:
- Main theme (
clean-academic.scss) -> full design-principles audit (.claude/rules/slide-design-principles.md) - Legacy theme (
clean-academic-legacy.scss) or SUNY's own theme -> legacy audit only (overflow, spacing); skip density limits
- Main theme (
-
Screenshot every slide:
python3 scripts/shoot_slides.py $ARGUMENTS --out /tmp/$ARGUMENTS-shotsThis renders the html first when it is missing or older than the qmd, then writes one 1280x720 PNG per slide in reading order (vertical stacks included). Read every PNG - the pixels catch what the source hides: real overflow, wrapped bullets, a figure that failed to load, a video slide stuck on a black frame. (
bash scripts/preview.sh <name>still opens the deck in a browser when you need to interact with a slide.) -
Audit every slide for:
DENSITY (new decks, budgets from the profile JSON): >1 core message, more bullets than
bullets_max(bullets_max_with_figurewith a figure; one less again if any bullet wraps to two lines), more wrapped bullets thanbullets_max_two_line, any three-line bullet, more colored boxes thanbox_density, nesting deeper thanmax_nestingOVERFLOW: Content exceeding slide boundaries - confirm on the PNGs FONT CONSISTENCY: Any.smaller/.smallestin a new deck (forbidden), inline font-size overrides below 1em CENTERING (new decks): ad-hoc positioning fighting the theme, unjustified{.top-align}or{.left}, a deck that re-enablesauto-stretchover theQuarto/_quarto.ymlproject default of false (or a_fixtures/qmd that fails to repeat it - fixtures sit outside the project defaults) BOX FATIGUE: more boxes on one slide than the budget, wrong box types LAYOUT: Missing transitions, missing framing sentences, semantic colors
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.
- 4d ago First seen · 74 lines · 46 tokens per session scan A 9cd2ca993a61
visual-audit is a skill published in the GitHub repository alohays/paper2pr (5 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 857 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.
Other skills, from other repositories
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.