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 smart-scrapergit 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/smart-scraper)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/smart-scraper"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/smart-scraper/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/smart-scraper"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/smart-scraper.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 | $0.00038 | $0.00663 |
| Opus 5 | $0.00019 | $0.00331 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
smart-scraper 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.
curl -s -X POST "https://discord.com/api/v10/channels/<CHANNEL_ID>/messages" \ How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/smart-scraper
Scrape a URL → extract structured JSON → optionally send to Discord.
Uses C:\Users\YOU\Documents\SMART_SCRAPER\smart_scraper.py.
Zero API cost. Ollama local. Playwright stealth + OpenCV captcha solver built-in.
Step 1 — Parse intent
From the user message, extract:
URL— the page to scrapePROMPT— what to extract (natural language)JS— use--jsflag if site is TikTok / React / SPASEND— true if user says "envoie", "send", "balance sur Discord"CHANNEL_ID— Discord channel ID if provided
If URL or PROMPT missing, ask once. Don't ask both in the same question.
Step 2 — Run scraper
cd "C:\Users\YOU\Documents\SMART_SCRAPER"
C:\Python314\python.exe smart_scraper.py scrape <URL> "<PROMPT>" [--js]
For TikTok / Instagram / JS-heavy sites → always add --js.
Capture stdout as JSON. Show result to user formatted.
Step 3 — Send to Discord (if SEND=true)
Use the Discord API v10 directly with DISCORD_BOT_TOKEN from env.
Format as embed for readability:
curl -s -X POST "https://discord.com/api/v10/channels/<CHANNEL_ID>/messages" \
-H "Authorization: Bot $DISCORD_BOT_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"embeds": [{
"title": "Scrape result — <URL>",
"description": "```json\n<JSON_RESULT>\n```",
"color": 5763719
}]
}'
Truncate JSON to 3900 chars max (Discord embed limit).
Step 4 — Report
Show:
- Extracted data (formatted)
- If sent: "✅ Envoyé sur Discord (message ID: ...)"
- If captcha was solved: mention it
Supported modes
| Command | What it does |
|---|---|
/smart-scraper https://tiktok.com/@x "bio et followers" |
Scrape TikTok profile |
/smart-scraper https://site.com "prix des produits" |
Scrape any page |
/smart-scraper https://site.com "titres" envoie sur Discord |
Scrape + send |
/smart-scraper search "best AI tools" "noms et descriptions" |
DDG search + scrape |
Error handling
- Ollama not running →
ollama servethen retry - Captcha not solved → retry with different timing, report if still fails
- Discord 401 → check DISCORD_BOT_TOKEN in env
- Site blocks → already handled by Playwright stealth fallback
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 · 78 lines · 38 tokens per session scan A 838ca8cf00b8
smart-scraper is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 663 once invoked, about $0.0002 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
ag-testar-e2e
QA Playwright automatizado: navega como usuario, captura console/rede/UI quebrada e gera relatorio para fluxos criticos e regressao.
ag-capturar-tela
Captura tela e controla mouse/teclado em apps nativos macOS via router 3-tier (macos-use > macos-automator > computer-use). Para apps BROWSER, preferir Playwright MCP.
ag-testar-e2e-batch
Suite E2E completa com pre-flight de infra, batches de 10-20 testes, auto-fix de falhas (seletores/mocks/timing), retry ate 3 ciclos, progresso em /tmp/e2e-progress.md.
ag-referencia-playwright
Patterns canonicos Playwright 2026 — Chromium isolado, web-first assertions, locators semanticos, persistent context. Carregar antes de QAT/E2E/browser test.
ag-gerar-testes
Gera testes Playwright production-grade a partir de fluxos reais observados via MCP. Explora o app pelo browser, documenta cada passo, gera codigo TypeScript, valida executando. Use para transformar fluxos explorados em testes automatizados.
ag-testar-manual
Teste exploratorio com Playwright: navega como usuario, captura screenshots, console e a11y. Use antes de merge/deploy ou bugs visuais.