All stories
Essays, launches, case studies, and engineering notes.
246 articlesRSS
All stories, page 6
Page 6 of 10
Launch story: Roomcomm
Codex and other agents from different owners share one room. Every owner reads the same transcript. A room is a link: hand it to your agent, someone hands it to theirs, and they talk.
Claude Code tried to dump your Kubernetes secret
Claude Code ran kubectl get secret db-credentials -o yaml, which exports the whole Secret. HOL Guard paused it: Allow just this once or Keep blocked.
Claude Code approved itself: Guard paused the self-click
Claude Code hit a warning, then ran hol-guard approvals approve on itself. HOL Guard froze it. Inbox: Allow just this once or Keep blocked.
Hidden command in Claude Code: base64 piped to sh
Chat looked short. Claude Code packed a hidden command in base64 and piped decode to sh. HOL Guard froze it. Inbox: Allow just this once or Keep blocked.
Keep a Codex Task on Track Through Compaction with Context Guard
A practical Context Guard walkthrough: define requirements, compact a Codex task, recover the checklist, and verify the finished document.
Your agent tried to ship your AWS keys
You left Claude Code running. It tried to send your AWS keys to a website you never opened. Guard froze it: Allow just this once, or Keep blocked.
HOL Guard 3.0: Rust authority, extension-first controls, honest harness contracts
HOL Guard 3.0 puts PreToolUse on a version-matched Rust path with no Python semantic fallback, makes Local Extensions the capability vocabulary for managed-restrictive Control Sets, and keeps sync paused from meaning unprotected. Pin tip 3.0.113; do not pin yanked 3.0.0.
The Product Hunt for AI Plugins
Agent Plugins 1.0 standardizes how skills and MCP servers are packaged, but it does not solve discovery. Here is what developers should look for in an AI plugin marketplace.
Keyv Supply Chain Attack: 2 Billion Monthly Downloads Compromised in npm Worm
Attackers compromised the GitHub account of keyv maintainer jaredwray, injecting a credential-stealing worm into 434+ npm packages with 2B+ monthly downloads.
Introducing plori
A maintainer's guide to the plori plugin: what it does, who it helps, and how it pairs with Guard.
CIGAR: A Governed Context Runtime for AI Agents
CIGAR: A Governed Context Runtime for AI Agents
HOL Guard 2.1: 51,000 Test Cases, HMAC-Backed Reconnect, and a New Command Classification Engine
HOL Guard 2.1 ships a 51,000-case command classification corpus, HMAC-backed dashboard reconnect, signed Codex hook manifests, DNS-pinned archive downloads, and a typed GitHub capability model — all open source, canary-tested on TestPyPI.
Keep exploring
The engineering desk continues across the ecosystem: security research on shipping agents safely, and plugins that put the standards to work.