Foogle.eth

| Buy High Sell Low |

[Foogle.eth @Foogle_ETH]

🗣️🗣️🗣️

[مجلاد بن مشاري السبيعي @Al7lhh223]

لكل مهتم بالأمن السيبراني وأختبار الاختراق
هنا دليل وكنز ومختصر حقيقي!

تجمع لك خريطة الطريق كاملة في مكان واحد:
- أهم ثغرات الويب (OWASP).
- طرق فحص السيرفرات والمنافذ المفتوحة.
- خطوات تصعيد الصلاحيات واختراق الشبكات.

مرجع سريع وجاهز لطلاب شهادة OSCP
ومختبري الأختراق عشان يراجعون خطواتهم وأوامرهم بلمحة واحدة!

https://t.co/OQaUXCj1iX

#الامن_السيبراني #Cybersecurity #Pentesting

[Vivek | Cybersecurity @VivekIntel]

The Book of Secret Knowledge: A Curated Goldmine for Cybersecurity, DevOps & Linux Professionals

🔥 One of the best free knowledge repositories for tech professionals.

Packed with tools, cheat sheets, blogs, tutorials, one-liners, security resources, and learning materials for Linux, networking, DevOps, and cybersecurity.

🔗 https://t.co/S1fjZzUqaB

#CyberSecurity #Linux #DevOps #Pentest #Networking #OpenSource

[Tony Robbins @TonyRobbins]

Reminder: class is in session. It's called LIFE. Don’t waste a minute.

— from Saint-Tropez, with love

[Mastery Mindset @_masterymindset]

She literally shows how to cure laziness and stop procrastination from blocking your success !!

[International Cyber Digest @IntCyberDigest]

AI isn't taking our jobs. It's keeping cybersecurity people employed for life.

[Alex Hormozi @AlexHormozi]

Do not hang out with losers. It is contagious.

[ClaudeDevs @ClaudeDevs]

We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.

Available for all Claude Code users. Install from the plugin marketplace (/plugins).

[Tom Dörr @tom_doerr]

Pentesting guide with tools, labs, and certifications

https://t.co/F0BW5YgmCt

[solst/ICE of Astarte @IceSolst]

Claude code’s /security-review is just a Skill, and the whole prompt is in this repo

It’s p generic and imo you can tailor it to each repo to language you’re scanning to get better results

https://t.co/1a4puZSASL

[Muqsit 𝕏 @mqst_]

📝 Beginners Guide: Networking Basics for Pentesters

Part 1: https://t.co/VOsrhZQluB
Part 2: https://t.co/ZtWooLpZ0f
Part 3: https://t.co/6ZeeOeXT94

#networking #infosec

[aditya @adxtyahq]

“design a RAG pipeline for 10M docs with zero hallucination”

apparently this was asked in a Google L5 interview round. came across it somewhere on the internet and honestly it’s a way more interesting system design problem than most classic distributed systems questions

1. ingest + normalize docs
- remove duplicates, standardize formats, extract metadata, maintain version history

2. hybrid retrieval (BM25 + embeddings)
- BM25 handles exact keyword matching while embeddings capture semantic meaning
- semantic search alone usually struggles with precision at massive scale

3. ANN retrieval + reranking
- ANN (Approximate nearest neighbor ) quickly pulls top candidate chunks from millions of docs
- then a reranker rescoring step improves relevance by deeply comparing query vs retrieved chunks

4. source confidence scoring
- every retrieved chunk gets scored based on freshness, trust level, overlap and retrieval consistency
- low-confidence context should never heavily influence generation

5. constrained generation
- the model is only allowed to answer using retrieved context (nothing new to be invented outside of the retrieved context)

6. citation-backed responses
- every major claim links back to exact chunks, documents or timestamps

7. hallucination fallback layer
- if retrieval confidence drops below a threshold: “insufficient evidence found”

8. continuous evals
- run adversarial queries, retrieval recall benchmarks and hallucination tests continuously

9. caching + memory layer
- cache high-frequency enterprise queries and retrieval paths (improves latency and output)

10. observability everywhere
- trace retrieval paths, chunk rankings, token attribution and failure points

Also at 10M docs, retrieval quality matters more than the frontier model itself.

[Shraddha Bharuka @BharukaShraddha]

🚀 ALL FREE CERTIFICATION RESOURCES

Level up your skills for FREE 👇

☁️ AWS

https://t.co/ovidgG7QkI

🔐 CISSP

https://t.co/VuNIDrmo2u

🛡️ CISA

https://t.co/1GJFYvihoq

📊 CISM

https://t.co/7mESc0zMyH

⚡ CRISC

https://t.co/kHWfBtHay7

📈 Digital Marketing

https://t.co/kHWfBtHay7

📌 Save this for later
🔁 Retweet to help others
🎯 Follow for more free tech resources 🚀

[Nainsi Dwivedi @NainsiDwiv50980]

Your AI outputs look messy because you built prompts

not a system

Claude Code becomes insanely powerful when you structure it like an actual AI operating system

That’s the unlock most builders miss

Here’s the framework:

→ CLAUDE.md
The central brain

Store architecture rules, workflows, conventions, project memory, coding standards, deployment instructions, and context Claude should never forget

→ Skills
Turn repeated workflows into reusable capabilities

Instead of rewriting prompts for debugging, refactoring, writing APIs, reviewing code, or shipping features…

you create modular skills Claude can invoke instantly

→ Hooks
Automate quality control

Run linting
Block dangerous actions
Trigger validations
Enforce standards
Send notifications
Auto-review outputs

without manually checking everything yourself

→ Subagents
Build specialized AI workers

One researches
One writes
One reviews
One tests
One ships

Now Claude stops acting like a single assistant

and starts operating like a coordinated engineering team

→ Plugins + MCP Servers
Connect your entire stack

GitHub
Databases
APIs
Internal tools
Automation systems

This is where autonomous workflows actually begin

Because now your workflow becomes:

Plan → Delegate → Execute → Validate → Improve

The result?

• cleaner repositories
• persistent AI memory
• reusable workflows
• faster execution
• less context loss
• dramatically higher output quality

Claude Code is not just a coding tool

It’s infrastructure for building scalable AI systems

[NSA Cyber @NSACyber]

NSA is releasing security design considerations for AI-driven automation leveraging MCP which, while simplifying the integration of diverse capabilities into powerful agent workflows, requires caution. Learn more: https://t.co/zn2DyUz5be

[Anuj @anujcodes_21]

Google CEO tries to tell University students to love AI.

They tell him to BOO off.

This is what most people think of the hated AI, we don't want it.

Watch it and bookmark it now.

[unusual_whales @unusual_whales]

BREAKING: We just gave Claude access to the entire options and stock market.

It's the Unusual Whales MCP Server. It plugs directly into any AI assistant and gives it live, structured data on demand.

Build a trading bot. Build a finance dashboard. Build whatever you want.

[Bilgin Ibryam @bibryam]

AI Agent Governance Toolkit - by Microsoft

Runtime governance for AI agents through deterministic policy enforcement, zero-trust identity, execution sandboxing, and SRE for autonomous agents. Covers all 10 OWASP Agentic risks with 13,000+ tests.

https://t.co/sONejSjsrX

[ZARA @HeyZaraKhan]

100 Claude Repos that will completely change your life:
(save this)

1. Terminal AI coding agent https://t.co/gkTwIb7T9s
2. Ready-to-use starter apps https://t.co/PtEclReNCv
3. Official agent skills https://t.co/1RZ7lpP3xB
4. Plugin marketplace https://t.co/GVeknTu56n
5. Full ecosystem https://t.co/HOkmGrvrvL
6. Master list https://t.co/BVrGRmcQdV
7. 1000+ plugins https://t.co/8lzXVbeps2
8. Huge skills library https://t.co/wnArbr7a7N
9. Curated skills https://t.co/apIhhs1UEG
10. Cross-platform skills https://t.co/7wcdPfFLSh
11. LLM pipelines https://t.co/iqzPWyUrXk
12. Agent workflows https://t.co/bXPebvjN4v
13. Multi-agent systems https://t.co/o6NGMPl9h7
14. Team-based agents https://t.co/Ay1jn8wFpZ
15. AI dev team https://t.co/IXZNK0ym7r
16. Code agents https://t.co/Uq0aHekO6Y
17. Auto PR fixes https://t.co/zbCEAnFHlD
18. AI coding assistant https://t.co/rAeiD6uphU
19. Code search https://t.co/gDIpT7KMs3
20. Agent standards https://t.co/S6YyQF6v8v
21. Productivity plugins https://t.co/xOowIKylVb
22. AI SDK https://t.co/eIYxaxaDLm
23. Memory layer https://t.co/mXiinRZafi
24. Voice agents https://t.co/mWSwV3YifX
25. Deploy agents https://t.co/NtTWJdcqx4
26. Web agents https://t.co/b8HiXRrI7G
27. Reasoning agents https://t.co/fMvI18BxYn
28. Long-term memory https://t.co/sJK9vrePQI
29. AI apps infra https://t.co/RYXlG8O4xD
30. API layer https://t.co/i7JfKyvYy1
31. Clean UI https://t.co/vqyN30JVso
32. Self-hosted UI https://t.co/mi8adckJBZ
33. Modern UI https://t.co/auzUkeggzf
34. Desktop app https://t.co/8yK33a3izg
35. Next.js clone https://t.co/9zpY0oN5Qv
36. Template https://t.co/2kkhJIIafG
37. Claude-ready UI https://t.co/yoaCZQco7W
38. Minimal UI https://t.co/dh9HOubWu8
39. Lightweight UI https://t.co/lr4f3N8CKv
40. Adaptable UI https://t.co/f6ekpq25Ik

That's a wrap
I hope you found this helpful
Follow me @HeyZaraKhan for more....

[Movez @0xMovez]

Microsoft Senior AI developer just showed how they build AI agents with Claude at Microsoft.

34-minutes. free. By Microsoft team

Opus 4.7 + 1,400+ pre-built MCP tools

plug Claude into agent → give it tools → ship to production

worth more than any $500 vibe-coding course.

[Nicolas Krassas @Dinosn]

A Claude Code skill bundle for bug hunting and external red-team work - 51 skills, 15 slash commands, 574+ disclosed-report patterns curated across 24 vulnerability classes, plus enterprise identity + infrastructure attack matrices. https://t.co/MpxsmCqaM3