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 zpoint/vibe-seller --skill qianniu-sharedgit clone --depth 1 https://github.com/zpoint/vibe-sellerWrote 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/zpoint/vibe-seller/qianniu-shared)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/qianniu-shared"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-shared/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/zpoint/vibe-seller/qianniu-shared"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/qianniu-shared.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 97 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00172 | $0.02501 |
| Opus 5 | $0.00086 | $0.01251 |
| Sonnet 5 | $0.00034 | $0.00500 |
| Haiku 4.5 | $0.00017 | $0.00250 |
Grade A, and why
qianniu-shared 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qianniu (Taobao/Tmall) — Shared (auth, navigation, common patterns)
What every 千牛 seller task needs: the workbench login (chrome backend,
human-in-the-loop), the 生意参谋 / 万相台无界 page map + SSO, the per-store
download directory, and the CSV encoding caveat. Operation-specific skills
(qianniu-listing, qianniu-ads) load this first.
These stores run on the chrome browser backend (not Ziniao) — check
stores.browser_backend. There is no auto-captcha here: the slider captcha and SMS are HUMAN steps (§ 2).
browser-use 0.13 CLI (heredoc). Drive the wrapper by piping a Python snippet:
~/.vibe-seller/bin/<slug>/browser-use <<'PY' … PY. Pre-imported helpers:new_tab(url)(first navigation, notgoto),page_info(),js("<javascript>")(runs JS in the page, returns the value; pierce open shadow roots via.shadowRoot),click_at_xy(x, y),capture_screenshot(path),wait_for_load(),cdp("Domain.method", ...)(raw CDP). See thebrowser-harnessskill. Gotcha:cdp(...)/click_at_xy(...)are Python helpers in the heredoc scope — do NOT call them inside ajs("…")string (that runs in the page, where they're undefined).
First-run on a fresh box: the chrome backend needs Playwright's headed Chromium ("Chrome for Testing"). If
browser/startfails with "Executable doesn't exist at …/chromium-/…Google Chrome for Testing", install it once:.venv/bin/python3 -m playwright install chromium.
1. Surfaces & URLs
| Surface | URL | Notes |
|---|---|---|
| 千牛工作台 (workbench home) | https://myseller.taobao.com/ |
redirects to loginmyseller.taobao.com when logged out |
| 商品管理 (listings) | https://myseller.taobao.com/home.htm/SellManage/on_sale |
tabs: 全部 / 出售中 / 仓库中 / 预售 / 已售空 / 违规 |
| 生意参谋 (Business Advisor) | https://sycm.taobao.com/ |
retail big-data; product/traffic/transaction reports |
| 万相台无界 (Alimama, ad platform) | https://one.alimama.com/index.html |
hash-route SPA #!/...; ad plans + 报表 live here |
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 · 169 lines · 172 tokens per session scan A 9a9e703a2e39
qianniu-shared is a skill published in the GitHub repository zpoint/vibe-seller (66 stars, last pushed 3d ago), licensed Apache-2.0. It adds 172 tokens to every session and 2,501 once invoked, about $0.0009 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
ebay-search-listing
Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…
amazon-bestseller-listing
Amazon Best Sellers listing scraper: extract product cards from any Amazon Best Sellers (zgbs) or /gp/bestsellers/ category page — returns rank (position on chart), asin, title, url, image, imageAlt, price, stars, reviewCount, ratingRaw per item, plus category metadata (categoryName, categoryFullName, categoryUrl) and…
amazon-search-listing
Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
etsy-product-detail
Etsy product detail scraper: given an Etsy listing URL, returns full product detail including listingId, title, priceCurrent, priceOriginal, currency, images (all), description, shopName, shopUrl, rating, reviewCount, favorites, inCartCount, variations (with per-option price ranges), highlights, listedDate…
walmart-product-detail
Walmart product detail page extractor: given a walmart.com product URL (walmart.com/ip/...), extract full product data including itemId, title, brand, model, UPC, price, wasPrice, currency, availability, category path, seller info, all images, shortDescription, longDescription, product highlights, full specifications…