All stories
Essays, launches, case studies, and engineering notes.
246 articlesRSS
All stories, page 3
Page 3 of 10
What is least privilege for AI agents?
A practical guide to least privilege for AI agents: limit identities, files, tools and access duration, with a worked support-ticket example.
Best Cursor Plugins in 2026
The best Cursor plugins in 2026: 10 picks with what each one loads into Cursor (rules, skills, agents, commands, hooks, MCP), HOL scan findings, verified install commands, example prompts, and pros and cons.
b2bsearch MCP: B2B contacts and account signals, with a spend cap on every call
Six MCP tools for B2B prospecting with b2bsearch Actors on Apify, including configurable per-call spend caps.
Covering Seminara MCP with HOL Guard
A guide to the Seminara MCP extension and how its tool rules work with HOL Guard's review policies.
Introducing CoMPaSS: An Analysis-First Prompt Framework for AI Agents
CoMPaSS is an unbenchmarked prompt framework that starts with user intent. Its creator explains the method and a plan to evaluate it.
ClickHouse RCE CVE-2026-116366: fixed versions and who is exposed
How to fix CVE-2026-116366: upgrade ClickHouse Server to 26.3.62.3-lts, 26.8.36.3-lts, 26.9.27.3-stable or 26.10.3.7-stable. ClickHouse says an unauthenticated user with network access can run code on the server under certain conditions. Cloud is already patched; Langfuse and SigNoz self-hosts ship off-support ClickHouse images.
Best Claude Code Plugins in 2026
Ten of the most-starred Claude Code plugins, one per job, with the HOL scan findings behind each label and install commands from each README.
My Store Gave Away Every Product It Sold. The AI That Built It Never Noticed.
Gareth Hoyle found that anyone with a URL could download all 765 products from his AI-built Claude skills store for free. How it happened, four more problems the fix turned up, and the checks he now runs before shipping.
Your AI Isn't a Mind Reader. Stop Prompting Like It Is.
ART Prompt Framework structures AI prompts around a role, request, and terms. Its creator explains the approach and when to use it.
Your AI Agent Can Write Code. But Can It Think Like a Principal Engineer?
Principal Engineer OS is an open-source agent skill for examining engineering decisions, failure modes, and recovery before shipping code.
Launch story: Foundry, the growth ops kernel for ad agencies
An open-source growth kernel for ad agencies: audits, diagnoses, Arabic and English client reports, COD-aware ROAS maths and scheduled loops, with live budget changes locked behind a human.
Best Codex Plugins in 2026
The best Codex plugins in 2026 from HOL's scan data: 10 picks with a Safe security label, real GitHub stars, verified install commands, example prompts, and honest pros and cons.
Keep exploring
The engineering desk continues across the ecosystem: security research on shipping agents safely, and plugins that put the standards to work.