This is just an open thought\/notes post — using agents specifications files in an AI development environment.<\/p>\n\n\n\n
These kind of files are written in Markdown<\/a>, and can do some of these kind of things:<\/p>\n\n\n\n There’s an emerging standard, open source, called AGENTS.md<\/a>. Here’s their first page sample:<\/p>\n\n\n\n These can become very complicated. I’ve ran some tests developing a desktop image environment for VM Ware, and have specified a ton of applications, OS, etc. in these files.<\/p>\n\n\n\n Here is some of my experiment. It’s quite easy to generate such a file, and I was asking it to create a packer instance for VMWare”<\/p>\n\n\n\n But also — this remembers a lot of context.<\/p>\n\n\n\n Amazon has the same ides — rules for their “spec driven development” approach. Will probably discuss later as I have questioned them about the lifecycle of biz rules in a development cycle, but, generally stores all the info of your dev environment for your project. Generally, is stored in .amazonq\/rules, though can be in a file like amazonq.rules.<\/p>\n\n\n\n Also Anthropic has the CLAUDE.md<\/a> file, which is like AGENTS. It’s loaded at startup to give your agent context, among other things. There is also use of a json file for settings.<\/p>\n\n\n\n From CLAUDE site:<\/p>\n\n\n\n Note that these other AI agents will in fact read AGENTS.md, even if they put up a fight against you. Also, be aware that in general you’ll eventually be checking in and maintaining these files for your projects.<\/strong><\/p>\n\n\n\n Thoughts. Well, after working with these, it’s nice to have a context on loadup mechanism. It would be nice to share among other developers. That said, I wonder how this is going to play into the specs in maven, ivy, ant, gradle etc. files. Why not just read those files, instead of in some cases having a double entry? <\/p>\n\n\n\n And since this is now emerging, there are several standards — am guessing if you ever switch AI providers it could convert the standards (from say Q rules to CLAUDE) with no fuss. It had better, being that conversions seems to be one of the AI strongpoints.<\/p>\n\n\n\n Another really nice related mechism is experimenting with saving chat contexts from the IDE. Amazon has something like this, and Claude can remember as well — but you could technically store prompt history offline, even incorporate the best answers into the md files.<\/p>\n\n\n\n Best thing is to try all of this out.<\/p>\n\n\n\n References:<\/p>\n\n\n\n MARKDOWN<\/a><\/p>\n\n\n\n AGENTS.md<\/a><\/p>\n\n\n\n CLAUDE Settings<\/a><\/p>\n\n\n\n\n
\n
\n
# AGENTS.md\n\n## Setup commands\n- Install deps: `pnpm install`\n- Start dev server: `pnpm dev`\n- Run tests: `pnpm test`\n\n## Code style\n- TypeScript strict mode\n- Single quotes, no semicolons\n- Use functional patterns where possible<\/pre>\n\n\n\n
# DVM Virtual Dev Environment\n\n## Project Overview\nThis project creates a Ubuntu 24.04.3 desktop virtual machine using HashiCorp Packer and VMware. The VM is pre-configured with development tools including Visual Studio Code and IntelliJ IDEA Community Edition.\n\n## Purpose\n- Build standardized development environments\n- Automate VM provisioning with consistent tooling\n- Provide reproducible Ubuntu desktop environments for development work\n\n## Key Components\n\n### Packer Configuration (`ubuntu-desktop.pkr.hcl`)\n- **Base Image**: Ubuntu 24.04.3 Desktop AMD64 ISO\n- **Platform**: VMware (vmware-iso builder)\n- **Resources**: 4GB RAM, 2 CPUs, 40GB disk\n- **Authentication**: SSH with ubuntu\/ubuntu credentials\n\n### Provisioning\nThe build process installs:\n\n**Development Tools:**\n- Microsoft Visual Studio Code\n- IntelliJ IDEA Community Edition\n- Docker Desktop\n- Postman\n- MySQL Workbench Community<\/pre>\n\n\n\n
\n
Key points about the configuration system<\/h3>\n\n\n\n
\n
\/command-name<\/code><\/li>\n\n\n\n\u200b<\/a><\/a><\/h3>\n<\/blockquote>\n\n\n\n
\n\n\n\n
\n\n\n\n