Skip to main content
Gordon Beeming

Father • Husband • Triathlete • SSW Solution Architect

homeblognuggetsprojectstagsabout
← all tags

Tagged Skills

3 postsRSS ↗
Sep 15, 2026·5 min read

Experimenting with automatic memory in Codex and Claude

After rewriting my skills and clearing memory, Codex and Claude felt better to use. My next experiment is to disable automatic memory, informed by research on context and memory poisoning.

AICodexClaude Code+2 more
Jun 18, 2026·4 min read

Your experience is a runtime dependency

AI agents are already very capable, but they don't automatically have the judgement that makes you effective in your current role. Skills and agent instructions are how you package that experience so the agent can use it.

AIAgentsAgentic Engineering+3 more
Apr 07, 2026·8 min read

Making Claude’s research cache an on-demand skill

I kept my research cache and skills, but removed the global trigger that made Claude load them on every task. Here is what worked, what added friction, and why I now invoke research when needed.

Claude CodeAISkills+3 more
About
Gordon Beeming

Solution Architect at SSW in Brisbane, and a Microsoft MVP every year since 2014. Azure, DevOps, and helping teams write better C#. Husband and father, usually training for the next swim, bike or run.

More about me »
Archives
202628202537202422023420228All 202 posts »
Search

Searches posts, projects and nuggets.

Tags
VSTS / TFSAIAzureProductivityVisual StudioYouTube VideosSecurityDevOps.NETPowerShellGitHub
Elsewhere
GitHubLinkedInYouTubeRSS feed
xylemGordon Beeming

A personal blog about software development, DevOps, open source, and the occasional triathlon story. Built with Next.js.

Powered by curiosity and

Links
blognuggetsprojectstagsaboutcolor palette
Support
Buy Me a CoffeePatreonGitHub Sponsors
© 2013-2026 Gordon Beeming · Opinions are my own and not that of my company or anyone I engage with.