| https://x.com/josephzengx | |
| Github (For Verification) | https://josz5930.github.io/ |
| Codeberg | https://codeberg.org/josz5930 |
š Idea ā working code in one sitting.
Ran the BMad Method Framework through Grok Build Beta (early access dropped for SuperGrok on 25 May) this weekend 
. The framework gives you a clear, repeatable path from vague idea to production-ready implementation.
Full workflow map here:
https://docs.bmad-method.org/reference/workflow-map/
Start a sandbox and ship something today 
P.S. I use sbx for my sandbox (https://docs.docker.com/ai/sandboxes/agents/shell/)
Just shipped pii-redact-md-sg- a local Python tool that redacts PII from PDFs & CSVs before anything touches a remote LLM.
SG NRIC, mobile, postal + Luhn/NRIC validation ā¢ deterministic placeholders ā¢ second-pass audit that blocks leaks ā¢ Text friendly format ā¢ Fully offline.
Building for secure AI workflows .
GPT-5.4-Cyber released by OpenAI for Cybersecurity use
https://openai.com/index/scaling-trusted-access-for-cyber-defense/
Building an Automated Pipeline with LangChain DeepAgents to Find Zero-Days in Kernel Drivers
https://blog.ahmadz.ai/automated-deepagents-langchain-pipeline-for-zero-days/
I had $100 in unused Google Cloud credits from my Google One Ultra plan and figured Iād put them toward something interesting. Over the long weekend I ended up building an automated pipeline that scans thousands of Windows kernel drivers for exploitable vulnerabilities, specifically looking for ones that can be used in BYOVD (Bring Your Own Vulnerable Driver) attacks. On its first real run on a massive driver pack, it successfully flagged a zero-day in an ASUS driver.
"TOTALLY HARMLESS LIBERATION PROMPTS FOR GOOD LIL AI'S!"
"Production-ready AI agents need production-grade governance."
Microsoft's Agent Governance Toolkit for:
ā¢ Security & access controls
ā¢ Policy enforcement
ā¢ Audit & compliance guardrails
AI Agent Governance Toolkit ā Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. - microsoft/age...
Android Reverse Engineering & API Extraction ā Claude Code skill
https://github.com/SimoneAvogadro/android-reverse-engineering-skill
[un]prompted Conference - A NoteBookLM containing videos and transcripts.
Appropriately, you can ask questions of the content š
https://notebooklm.google.com/notebook/78ee3710-1741-488d-af06-159f518e9510
During the Chinese New Year holidays, I was trying out Roo Code in VS Code.
Something that bugged me since the release of the CDC voucher scheme was the question "How much value do you put on the vouchers?"
Here is how the PoC version was generated:
The reason why it was mostly DeepSeek is cos I got some credits on DeepSeek platform and so far it is good enough since I do not have much money to spend š
