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.
git 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/commands/ertinox7711/sgrr-agi-v2/scrape403)<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/scrape403"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/scrape403/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/commands/ertinox7711/sgrr-agi-v2/scrape403"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/scrape403.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 | $0.00049 | $0.00618 |
| Opus 5.5 | $0.00020 | $0.00247 |
| Sonnet 5.5 | $0.00010 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
scrape403 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 1mo 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.
Des qu'un `WebFetch`, un `curl`, un `https.get` Node ou un `requests` Python What it actually says
Cible : $ARGUMENTS
Des qu'un WebFetch, un curl, un https.get Node ou un requests Python
rend 403, 429, 503, une page vide ou un challenge, la reponse n'est pas
« c'est bloque » : c'est de passer a l'outil suivant. Ne jamais abandonner sur
un 403, ne jamais bricoler des User-Agent a la main.
L'ordre a suivre
- La page exige-t-elle une session connectee ? Alors ce n'est pas un
probleme de bot-block : passe par
hbrowse, qui pilote le Brave dedie ou les comptes sont deja ouverts.wsl -u YOU -- bash -lc 'hbrowse text "<url>"'(verbes :textinfodomsnapshotscreenshot <out.png>click <sel>eval <js>. Unrc=3veut dire URL interdite par la denylist — zone Shopify/OFM protegee — pas une panne.) - Sinon, Scrapling. Ecris un fichier
.py(jamaispython -c: PowerShell mange les$et les backticks), avecsys.stdout.reconfigure(encoding='utf-8')en tete, sinonUnicodeEncodeErrorcp1252 des le premierprint.
from scrapling import StealthyFetcher, Fetcher
# 1er essai — Playwright stealth, passe les challenges JS Cloudflare
page = StealthyFetcher.fetch('https://cible.com', headless=True, network_idle=True)
html = page.html_content
# variante rapide — empreinte TLS Chrome (curl_cffi)
page = Fetcher.get('https://cible.com', impersonate='chrome')
html = page.html_content
- Installation si absent :
pip install scrapling && scrapling install(telecharge un Chromium stealth, une seule fois). - Dernier recours si Scrapling echoue aussi : MCP Playwright
(
browser_navigate+browser_evaluatepour extraire le DOM).
Apres coup
Ne memorise rien si c'etait un 403 ordinaire — le reflexe Scrapling est deja une regle globale. Ne note dans la memoire du projet que si ce domaine precis demande une astuce particuliere : cookie de session, en-tete maison, selecteur DOM non evident.
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.
- 1mo ago First seen · 51 lines · 49 tokens per session scan A 9f64a0c1ea2f
scrape403 is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 618 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
act
Live agentic desktop + browser control via OAuth (no API key).
linkedin-apply
Review the nightly LinkedIn Easy Apply queue with the candidate, then submit the approved jobs through Claude in Chrome.
myunsw
Automate myUNSW operations (enrollment, grades, timetable, fees, personal info) via AI agent + curl.
r
Resume the last handoff and carry on with the outstanding work.
crear-skill
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar skill", "nueva habilidad". Usa el workflow: draft → test → review → improve → repeat con evaluación cuantitativa y qualitative review.
setup-aliases
Add the following bash aliases to /.bashrc for quick Claude Code commands.