Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KristenPan/pickoo-your-favoritesnpx agentmods add skills/kristenpan/pickoo-your-favorites/redskillWrote 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/kristenpan/pickoo-your-favorites/redskill)<a href="https://agentmods.dev/skills/kristenpan/pickoo-your-favorites/redskill"><img src="https://agentmods.dev/badge/skills/kristenpan/pickoo-your-favorites/redskill/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/kristenpan/pickoo-your-favorites/redskill"><img src="https://agentmods.dev/badge/skills/kristenpan/pickoo-your-favorites/redskill.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 | $0.00082 | $0.00789 |
| Opus 5 | $0.00041 | $0.00394 |
| Sonnet 5 | $0.00016 | $0.00158 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
pickoo-your-favorites 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickoo！AI收藏夹助手
Pickoo is a complete local-first AI favorites assistant with a browser frontend, local Node.js server, shared task journal, and three bundled Agent Skills. It turns submitted public links into editable Markdown, source evidence, OCR text, timestamped transcripts, semantic chapters, and reusable ideas and content assets.
Pickoo is for anyone who collects information to remember, understand, or find inspiration. Creators are an important use case, not the product boundary.
The top-level pickoo-your-favorites Skill is the product entry point. The bundled save-to-favorites, creator-content-ingest, and asset-review-agent Skills are internal workflow components; do not present or invoke any one of them as a replacement for Pickoo.
What Pickoo does
- Accepts complete share text or public links from Xiaohongshu, WeChat, Douyin, Bilibili, Xiaoyuzhou, music services, articles, podcasts, and general webpages.
- Routes every new collection through one duplicate-aware intake before capture, OCR, ASR, semantic organization, and evidence review.
- Preserves source text, media, timestamps, processing state, and user edits instead of replacing the source with an AI summary.
- Provides a complete local browser interface for reading, playback, search, collections, tags, likes, notes, saved images, frames, clips, quotes, viewpoints, hooks, and structures.
- Reuses compatible local OCR and ASR runtimes first and prepares isolated optional runtimes only after the user approves installation.
Authorization boundary
Before the first dependency installation, runtime/model download, browser login connection, or Agent Skill installation, explain the action and ask for user approval. Ordinary capture may access only the links the user submitted and the configured Pickoo library.
Read docs/PERMISSIONS.md before setup or any operation involving browser state, local Agent folders, media downloads, OCR, ASR, or private sessions.
Start
- Confirm Node.js 20+ and Python 3.10+ are available.
- In this Skill directory, install Node dependencies with
npm cionly after approval. - Install Python dependencies from
skill-source/creator-content-ingest/requirements.txtonly when capture is requested and after approval. - Start with
npm startand openhttp://127.0.0.1:4324. - Let the user choose a library in settings, or use
PICKOO_LIBRARY_ROOT. Never infer a personal Obsidian or another project's path.
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 · 52 lines · 82 tokens per session scan A d43a8002b0bc
pickoo-your-favorites is a skill published in the GitHub repository KristenPan/pickoo-your-favorites (17 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 789 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
Use whenever the user works with PDF files — reading/extracting text from PDFs (lecture notes, textbook chapters, HW problems, HW solutions, hand-written answers), converting PDFs to markdown for downstream analysis, merging/splitting PDFs, or creating PDFs. For scanned or hand-written PDFs, OCR is required…
cv-update-review
Run a confirmation-gated CV update workflow for Word CV documents: set up a reusable profile, scan configured local activity sources plus public evidence such as PubMed through NCBI E-utilities and configured website/RSS feeds, prepare a CV update packet, ask the user to approve completed/public/accepted items, create…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.