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 Ertinox7711/SGRR-AGI-V2 --skill aliexpress-source-mappinggit clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2Wrote 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/ertinox7711/sgrr-agi-v2/aliexpress-source-mapping)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/aliexpress-source-mapping"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/aliexpress-source-mapping/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/ertinox7711/sgrr-agi-v2/aliexpress-source-mapping"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/aliexpress-source-mapping.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 | $0.00145 | $0.01981 |
| Opus 5 | $0.00072 | $0.00991 |
| Sonnet 5 | $0.00029 | $0.00396 |
| Haiku 4.5 | $0.00015 | $0.00198 |
Grade A, and why
aliexpress-source-mapping scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Seul moyen fiable de passer l'anti-bot.** `WebFetch`/`curl`/`https.get` Node / in-app How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AliExpress source-mapping — reverse-sourcing d'un catalogue dropship
But : pour chaque produit d'une boutique (clonée depuis AliExpress via un concurrent), retrouver la fiche AliExpress d'origine, vérifiée par l'image, avec le nombre de commandes, sans jamais se tromper de produit.
DOCTRINE CENTRALE — reçus d'abord, devine ensuite
La cause n°1 des échecs passés = partir de devinettes (ids trouvés en SERP / vieux fichier non vérifié) au lieu de partir des reçus. Inverser cet ordre = la clé.
- Cherche le reçu AVANT tout. Un import réel laisse une trace : fichier fournisseur
(
*_fournisseurs_aliexpress.xlsxdans~/Downloads), mémoire projet (shop-b-import-*,*-source-*), note dans leCLAUDE.mddu dossier boutique. Ces liens = vérité maximale (ce sont les VRAIS achats). Ne jamais re-deviner un produit dont on a déjà le reçu. - Cross-check les candidats existants contre le reçu. Si un
candidates.json/ vieux XLS traîne : compare ses ids à ceux du reçu. S'ils matchent sur les produits connus → le fichier est fiable pour ceux-là, et ça isole exactement les produits restants (inconnus) sur lesquels concentrer l'effort. (SHOP-B : 12/12 boho matchaient → restaient 4 inconnus au lieu de re-traiter 23.) - Ne devine QUE le résidu. Tout le reste est déjà résolu.
PIPELINE
1. Catalogue live
https://<boutique>/collections/<coll>/products.json?limit=250&page=N (endpoint public
Shopify, pas d'auth). Extraire key/titre/handle/prix/image. Handle du produit =
t.split("|")[0] normalisé NFD sans accents.
2. Fiches AliExpress — Scrapling StealthyFetcher sur pages ITEM
Seul moyen fiable de passer l'anti-bot. WebFetch/curl/https.get Node / in-app
browser = 403/captcha/page vide. Ne jamais résoudre un captcha.
# fetchers, PAS `from scrapling import` (0.4.8+)
from scrapling.fetchers import StealthyFetcher
page = StealthyFetcher.fetch(f'https://fr.aliexpress.com/item/{cid}.html',
headless=True, network_idle=True, timeout=60000)
html = page.html_content
- Pages ITEM uniquement. Les pages search (
/w/…,/wholesale-…) = fines, lazy-loaded, polluées de pubs (même id sponsorisé revient sur toutes les requêtes) → inexploitables. Ne pas s'en servir pour matcher. - Extraire par regex :
og:image(image héro),subject/og:title(titre),tradeCount/…vendu|sold(commandes), urlsalicdn.com/kf/…\.(jpg|png|webp)(les images-variantes, précieuses — voir §4). PYTHONIOENCODING=utf-8obligatoire (Windows cp1252 crash). Prompts longs → Write un.pypuispython script.py, jamaispython -c.- Scrapling lent (Camoufox ~15-40 s/fiche) → run_in_background, poll le
.jsonfinal.
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.
- 3d ago First seen · 120 lines · 145 tokens per session scan A 94c27c6a16be
aliexpress-source-mapping is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 4d ago), licensed MIT. It adds 145 tokens to every session and 1,981 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other skills, from other repositories
should-i-buy
Helps the user decide on a purchase by taking the product links they're considering, asking a couple of sharp clarifying questions about their needs and circumstances, then opening each link in real Chrome via the Claude-in-Chrome extension to extract price, specs, ratings, reviews, return policy, and shipping.…
shop-research
Researches products across Amazon, Google Shopping, and relevant specialty sites using the Claude-in-Chrome browser extension. Finds candidates matching user-specified criteria (gift, gadget, gear, home goods, etc.), captures screenshots and key data per candidate, then generates a modern 2026 HTML report with…
workflow-optimization
Read the customer request, account record, and supplied policies before choosing an action. Policy overrides the customer's requested remedy.
apparel-demand
Analyzes apparel demand prediction systems for trend forecasting, size curve optimization, color and style analytics, sell-through rate tracking, and markdown optimization following CPFR collaborative planning and GTIN product identification standards..
franchise-inventory
Analyze franchise inventory management for par level optimization, waste tracking and root cause analysis, and theoretical vs. actual usage variance.
merchandising-analytics
Analyze retail merchandising systems including planogram optimization (space-to-sales alignment, fair share index, sales per linear foot), visual merchandising effectiveness for in-store displays and e-commerce product pages, market basket analysis with association rule mining (Apriori.