Agent Entrypoints

AI agents entering a repository cold waste large amounts of context reconstructing repository intent, topology, and authoritative workflows. Humans do this naturally through exploration. Agents pay for it directly in tokens, latency, and incorrect assumptions.

An agent entrypoint is a compact machine-oriented routing layer embedded at the top of a repository README.md. Its purpose is to minimize exploratory context spend and direct agents toward authoritative operational paths immediately.

The goal is not to teach the agent the repository. The goal is to route the agent toward the correct sources of truth as quickly as possible.

This distills into a single question:

“How do I compress the minimum viable understanding of a repository into the fewest tokens possible while preserving reliable navigation and correct usage?”

Secret Zero - An Obvious Solution

What is Secret Zero?

In the realm of IT and security, “secret zero” refers to the initial bootstrap credential (or credentials) required to bring up a new deployment from scratch. Secrets classified as ‘secret zero’ are essentially the master keys that unlock further access or enable required functionality for an application.

This foundational set of secrets bootstraps secure communication and access to sensitive data, but it creates a chicken-and-egg dilemma: how do you securely manage the very first secret without exposing it? While secrets management tools like HashiCorp Vault or AWS Secrets Manager have revolutionized how we handle credentials, APIs, and tokens, secret zero remains a stubborn vulnerability lurking at the core of many projects.

LLM Underdogs of 2025

LLM Underdogs of 2025

2025 has been a flurry of AI madness that has been hard to keep up with. I’ve been deep in learning and experimenting in the AI space and noticed that while everyone’s hyping up the latest GPT variant or Claude release, there are some genuinely impressive open-source models that feel like they just flew under the radar in 2025. These aren’t just “good for their size”, they’re legit excellent models that you can run locally, for free, and deserve more attention.

Terraform Custom Module MCP Server

I created an MCP server that streamlines access to custom Terraform modules that I’d like to share with the community. The project called terraform-ingest is a CLI, MCP, and API tool that can be used locally or with an AI agent to tap into your existing code base more effectively.

Create Terraform with AI and Github Copilot

Creating terraform or other infrastructure as code for a new project can be daunting for some. This shows how you can easily crank out a new deployment to meet your requirements using Github copilot prompt files and a few free MCP servers. For the heck of it, we will also convert between two totally different cloud providers to deploy the same infrastructure.