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 sidiangongyuan/codex-skills-library --skill paper-share-htmlgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/sidiangongyuan/codex-skills-library/paper-share-html)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-share-html"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-share-html/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/sidiangongyuan/codex-skills-library/paper-share-html"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-share-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.02304 |
| Opus 5 | $0.00032 | $0.01152 |
| Sonnet 5 | $0.00013 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
paper-share-html 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Share HTML
Build a source-grounded paper presentation that works as a live talk first and as a readable static page second. Keep the narrative audience-facing: the page must present the research, not explain the editing process to the requester.
Read First
- Read references/editorial-style.md before drafting Chinese copy, quotations, or slide titles.
- Read references/visual-qa.md before extracting figures/tables or validating the finished page.
- Read references/visual-story-patterns.md before designing explanatory or synthesis diagrams.
- Use assets/template/index.html as a structural starter, not as a fixed slide count or visual theme.
Workflow
1. Ground the report in primary sources
Inspect the complete paper before drafting. Prefer the local PDF; otherwise use
the official publisher, arXiv, project, and code pages. Record the exact title,
authors, version, venue or identifier, project URL, code URL, and BibTeX when
available. Download the paper and supplementary material into source/ when
licensing and access permit.
Treat the paper as the source of truth for claims, metrics, captions, and quotations. Use external primary sources to verify cited work and full titles. Never reconstruct missing citation metadata from memory. If verification is not possible, mark it as unverified in working notes and omit it from the audience-facing page rather than guessing.
2. Ask one compact intake
After inspecting the supplied material, use request_user_input or the
available equivalent when the answers are not already known. Ask at most three
questions in one intake:
- audience and talk duration;
- emphasis: balanced, method, results, or critical discussion;
- delivery language.
Offer concrete choices and put the recommended choice first. If the tool is unavailable or the user does not answer, use these defaults:
What ships with it
8 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.
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 · 249 lines · 63 tokens per session scan A 135bfad8cbc7
paper-share-html is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 2,304 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
frappe-lms
Frappe LMS customization guidance for courses, batches, lessons, quizzes, assessments, enrollment, progress, certificates, portals, and learning workflows. Use when work touches Frappe LMS or education/training flows.
code-tour
Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests. Use when the user asks for a code tour, onboarding walkthrough, PR tour, or an…
codebase-onboarding
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.