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 MilkyWay008/Hermes-OTG --skill otg-web_extractgit clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGWrote 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/milkyway008/hermes-otg/otg-web_extract)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/otg-web_extract"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-web_extract/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/milkyway008/hermes-otg/otg-web_extract"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-web_extract.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 | $0.00050 | $0.01833 |
| Opus 5 | $0.00025 | $0.00916 |
| Sonnet 5 | $0.00010 | $0.00367 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
otg-web_extract 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 11d 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 -sL "https://r.jina.ai/https://TARGET_URL" How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
otg-web_extract — Web Content Extraction for OTG Hermes
TRIGGER: User gives a URL and asks to read, extract, fetch, summarize, or look up its content. Also triggers when a task needs page content (e.g. research, verification, data gathering).
HARD RULE — Extraction Priority (in this order, no exceptions):
Step 1: Jina Reader (r.jina.ai) ← ALWAYS try first — EXCEPT x.com URLs
Step 2: trafilatura (Python) ← when Jina fails/blocked; ALSO always used for x.com
Step 3: Headless browser ← final fallback when both above fail
When to use which (the golden rule)
| Site / Situation | Best tool |
|---|---|
| X.com / Twitter | trafilatura FIRST (Jina is frequently DDoS-blocked on x.com; trafilatura gets the raw HTML with the post text) |
| JS-heavy sites (grok.com, SPA apps, forums, dashboards) | Jina Reader (renders JS; trafilatura's static parse only gets the <title>) |
| Normal article / blog / docs page | Jina Reader (fast, clean markdown) |
| Jina returns error/blocked/empty | trafilatura next |
| trafilatura returns nothing / title-only | browser last |
| Login-gated content | browser only (both Jina + trafilatura fail behind auth) |
The complementarity rule: Jina is best for JS-heavy pages; trafilatura is best for X.com and anything Jina can't open — and things trafilatura can't open, Jina usually can. They cover each other's blind spots. Only when BOTH fail do you go to the browser.
Method 1 — Jina Reader (default first choice)
curl -sL "https://r.jina.ai/https://TARGET_URL"
Run via terminal. Replace TARGET_URL with the full URL.
- Output is clean markdown:
Title:,URL Source:,Markdown Content: - Free, no API key (anonymous)
- Strips prompt-injection from scraped content
- Do NOT retry Jina on YouTube — always 403 (bot detection). Go straight to browser.
- X.com — skip Jina entirely (see Method 2). Jina's x.com block is usually temporary (< 24h on first access), but don't wait for it.
- Rate limits: if 429/451/403, wait a few seconds OR fall through to trafilatura immediately.
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.
- 11d ago First seen · 170 lines · 50 tokens per session scan A 97020809114e
otg-web_extract is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 27d ago), licensed MIT. It adds 50 tokens to every session and 1,833 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
acquiring-disk-image-with-dd-and-dcfldd
Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.
implementing-cloud-trail-log-analysis
Implementing AWS CloudTrail log analysis for security monitoring, threat detection, and forensic investigation using Athena, CloudWatch Logs Insights, and SIEM integration to identify unauthorized access, privilege escalation, and suspicious API activity.
performing-cloud-log-forensics-with-athena
Uses AWS Athena to query CloudTrail, VPC Flow Logs, S3 access logs, and ALB logs for forensic investigation. Covers CREATE TABLE DDL with partition projection, forensic SQL queries for detecting unauthorized access, data exfiltration, lateral movement, and privilege escalation. Use when investigating AWS security…
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
hunt-django
Hunt Django-specific vulnerabilities: DRF permission gaps, ORM injection, and admin exploitation.