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 newsun-boki/literature-gallery-skill --skill literature-gallerygit clone --depth 1 https://github.com/newsun-boki/literature-gallery-skillWrote 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/newsun-boki/literature-gallery-skill/literature-gallery)<a href="https://agentmods.dev/skills/newsun-boki/literature-gallery-skill/literature-gallery"><img src="https://agentmods.dev/badge/skills/newsun-boki/literature-gallery-skill/literature-gallery/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/newsun-boki/literature-gallery-skill/literature-gallery"><img src="https://agentmods.dev/badge/skills/newsun-boki/literature-gallery-skill/literature-gallery.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 | $0.00069 | $0.00655 |
| Opus 5 | $0.00034 | $0.00328 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
literature-gallery 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature Gallery
Overview
Build a static paper gallery from structured paper metadata. Prefer the bundled template in assets/frontend-template/ unless the user already has an existing app that should be modified.
Workflow
- Inspect the current workspace and preserve existing user files.
- If starting a new project, run
scripts/create_gallery.py <destination>to copy the template. - Store papers in
data/papers.jsaswindow.PAPER_LIBRARY. - Each paper should include
id,title,authors,year,venue,area,keywords,cover,description,abstract,notes,links, andstatus. - Use real paper visuals for covers when possible:
- Prefer an official project teaser image when it is easy to identify and save locally.
- Otherwise use the first page of the paper PDF, cropped to the gallery card ratio.
- Store local cover files under
assets/covers/papers/and pointcoverto that path.
- Keep the frontend minimalist and light by default: clear grid, narrow borders, good whitespace, searchable filters, and a modal/detail view.
- Validate with
npm run checkwhenpackage.jsonexists, or at leastnode --check src/app.jsandnode --check data/papers.js. - For deployment, use Vercel for static hosting when requested. Add or keep
vercel.jsonand runvercel --prod --yesafter the user is authenticated.
Template
Use:
python3 /path/to/literature-gallery/scripts/create_gallery.py /path/to/new-project
The template is static HTML/CSS/JS and has no build step. It includes:
index.htmlsrc/app.jssrc/styles.cssdata/papers.jspackage.jsonvercel.json- placeholder SVG covers
Cover Generation
When generating covers from PDFs on macOS, Quick Look is a reliable fallback:
qlmanage -t -s 1800 -o /tmp/out paper.pdf
Then crop/resize the generated PNG to 1200x900 using Pillow. Keep the top of page 1 when no teaser is clear; this usually captures title/authors and often the first figure.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 282 B
- assets/frontend-template/assets/covers/hci.svg 1.4 KB
- assets/frontend-template/assets/covers/transformer.svg 1.1 KB
- assets/frontend-template/assets/covers/worldmodel.svg 1.4 KB
- assets/frontend-template/assets/covers/xr.svg 1.1 KB
- assets/frontend-template/data/papers.js 1.5 KB runs code
- assets/frontend-template/index.html 2.6 KB
- assets/frontend-template/package.json 203 B
- assets/frontend-template/src/app.js 7.5 KB runs code
- assets/frontend-template/src/styles.css 6.7 KB
- assets/frontend-template/vercel.json 50 B
- scripts/create_gallery.py 1.5 KB runs code
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.
- 12d ago First seen · 61 lines · 69 tokens per session scan A 868d96cd6154
literature-gallery is a skill published in the GitHub repository newsun-boki/literature-gallery-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 655 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
cli-ux
Use for packages/cli changes that affect command UX, prompts, help, output layout, progress, success, warnings, errors, JSON/stdout/stderr contracts, non-interactive/agent behavior, copy, or tests for those surfaces. Do not load for implementation-only refactors with unchanged CLI surface.
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
json-render-catalog
Skill "json-render-catalog" from yonatangross/orchestkit, covering json-render component catalogs, storybook → catalog import (#1529, 2026-04), new in 2026-04 → 2026-08 (json-render 0.14 → 0.20), directives — @json-render/directives (0.19) and registration.
julilaoshi-design
Public-safe julilaoshi-design workflow for official Pencil MCP execution and the free browser-first julilaoshi-design Web 2.0 editor. Use when a task needs Pencil handshake/canvas edits, .pen execution, screenshot review, or lightweight HTML design-to-web tweaking without redistributing official Pencil or leaking…
oil-frontend
A set of instructions for building and reviewing product front ends, meaning the visible part of an application that users interact with. It covers pages, components, forms, data flow, layout, styling, responsive behavior, and animations.
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.