setup

setup is a skill for Claude Code, Codex from ssrajadh/paperview. It costs 29 tokens per session (528 once invoked), scanned A, original, Apache-2.0.

A one-time setup command for PaperView, a local tool that creates narrated, animated explanations from research papers or codebases. It installs the Python environment, video-rendering dependencies, and local models.

In plain words
What is it for?
Use `/ppv:setup` to locate the PaperView project and run its setup script before using `/ppv:gen`.
Why use it?
It prepares everything required before generating a video, and it can safely be run again if setup needs to be repeated.

Skill for Claude CodeCodex

Part of the ppv plugin — 2 skills shipped together

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 skills/ssrajadh/paperview/setup
Any agent
npx skills add ssrajadh/paperview --skill setup
Clone the repo
git clone --depth 1 https://github.com/ssrajadh/paperview

Made for: Claude Code, Codex.

Or install ppv, the plugin that ships this one along with the rest of its 2 skills.

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssrajadh/paperview/setup.svg)](https://agentmods.dev/skills/ssrajadh/paperview/setup)
Your own site
<a href="https://agentmods.dev/skills/ssrajadh/paperview/setup"><img src="https://agentmods.dev/badge/skills/ssrajadh/paperview/setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 528 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 $0.00029 $0.00528
Opus 5 $0.00015 $0.00264
Sonnet 5 $0.00006 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 3d ago against content hash ff64e9990ce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 3d 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.

adapters/claude-code/skills/setup/SKILL.md · 37 lines

What it actually says

/ppv:setup — bootstrap the PaperView toolchain

Provision everything /ppv:gen needs to run locally. This is idempotent — safe to re-run.

Steps

  1. Locate the repo root + run the setup script — one block, so $REPO is in scope. Installed from the marketplace, this skill runs with $CLAUDE_PLUGIN_ROOT set to the plugin dir (adapters/claude-code), so the repo root (which holds core/ and scripts/setup.sh) is two levels up — no separate git clone required. Resolve it robustly, then run the script and stream its output:

    REPO="$(cd "${CLAUDE_PLUGIN_ROOT:-.}/../.." 2>/dev/null && pwd)"
    [ -f "$REPO/scripts/setup.sh" ] || REPO="$(git rev-parse --show-toplevel 2>/dev/null)"
    [ -f "$REPO/scripts/setup.sh" ] || REPO="$(find ~ . -maxdepth 6 -name setup.sh -path '*paperview/scripts*' 2>/dev/null | head -1 | xargs -r dirname | xargs -r dirname)"
    [ -f "$REPO/scripts/setup.sh" ] || { echo "couldn't find paperview repo — ask the user where it lives"; exit 1; }
    echo "repo: $REPO"
    bash "$REPO/scripts/setup.sh"
    

    If the resolver prints the error and exits, ask the user where they cloned/installed paperview, then run bash <that path>/scripts/setup.sh. The script creates ~/.paperview/venv with the ppv CLI, installs the Remotion node deps, checks ffmpeg, and warms the Kokoro TTS + Chromium models (first run downloads them — may take a few minutes).

  2. Confirm health by running the doctor and showing its output:

    ~/.paperview/venv/bin/ppv doctor
    
  3. Report success and tell the user they can now run /ppv:gen <pdf path and any options>. If ffmpeg was missing, tell them to install it and re-run setup.

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. 3d ago First seen · 37 lines · 29 tokens per session scan A ff64e9990ce0

Subscribe to this mod's changes

setup is a skill published in the GitHub repository ssrajadh/paperview (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 528 once invoked, about $0.0001 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 skills, from other repositories

remocn

Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…

Remocn/remocn · 88 tokens

frame-data-rollup

A native Remotion data frame — bars grow from zero by real data via spring physics while the figures roll 0→target in sync. The numbers come alive in a way a static HTML chart can't.

nexu-io/html-video · 46 tokens

douyin-cover

生成抖音、视频号、小红书等短视频封面图、视频标题图和合集封面,也能诊断和改版已有封面。用户说做封面、生成封面、抖音封面、视频封面、标题图、合集封面、3:4、4:3、1:1、短视频首图、动态封面首帧、给这期视频做图、这封面为什么没人点、帮我改封面、封面点击率怎么提升、诊断封面时都应使用。小白学AI系列封面除外:遇到“小白学AI封面/小白学AI第N集封面”时优先使用 xiaobai-ai-cover skill(系统内置 imagegen + 固定角色参考图)。这个 skill 会根据每次标题重新设计简约大方、有点击理由的封面,保留泊舟 IP 人物识别特征,内置「信息密度 ×…

bozhouDev/video-skills-toolkit · 374 tokens

music

Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata. For workspace video BGM, search the…

bozhouDev/video-skills-toolkit · 76 tokens

viral-video-benchmark

判断、扫描、拆解并归档抖音视频、小红书图文或小红书视频。实时读取用户同平台粉丝数并划分主对标池/跨级灵感池,用已登录浏览器读取目标作品和作者主页公开指标,再用确定性代码判定普通、小爆、爆款、现象级并扫描作者近 20 条候选;只对用户选中的爆款和现象级先构建可追溯证据包,再调用子 Agent 拆解,经确认后写入爆款库并合并或创建选题。用于“判断是不是爆款”“看看这个账号近20条有没有爆款”“拆解对标内容”“筛选同阶段对标”“爆款入库”“从爆款生成选题”“把同题内容归到一个选题”等请求;不用于自动监控。.

bozhouDev/video-skills-toolkit · 194 tokens

audio-to-subtitles

Convert local audio/video files or public media URLs into subtitle files by uploading local files to Cloudflare R2 and calling Volcengine AI MediaKit ASR subtitles API. Also supports MiniMax text-to-speech generation from text or text files, with optional subtitle generation from the produced audio. Supports batch…

bozhouDev/video-skills-toolkit · 124 tokens