Ask HN: How are you structuring Markdown-based context for AI coding agents?

3 pointsby lepuski4 mesi fa2 comments

I’ve recently transitioned from using LLMs in-browser to a local agentic workflow in VS Code (Gemini Code Assist). I can approve/disapprove changes which is nice, but I’ve hit a wall regarding context management. Initially, I provided all the whole repo as context to the non-agentic version of Gemini code assist and it performed well.

I read the agentic mode is "better" so to keep the agent aligned with my project's architecture, I’ve manually built 7 dense Markdown files that serve as the system instructions for the project. I require Gemini to update these files as we implement features.

gemini.md (instructs gemini to read the other md files and handle updating) project_overview.md, architecture.md, features.md, database.md, api.md, security.md

Each file is between 500–1,500 words so I’m concerned if f this is the right way to go. There seems to be no consensus on context file best practices. I’m seeing strong arguments for both minimalist, lean instructions and dense, project-wide specs. Honestly, the proper usage/prompting patterns of LLM's seems to be comparable to reading horoscopes, everyone goes by gut-feeling with the most cited source of truth being the confirmation bias.

How are you using .md context files in your workflow?

3 comments

catcam4 mesi fa

  We ran into this exact problem and ended up formalizing what we were doing into a small convention called HADS. Four
  block types in plain Markdown — [SPEC] for authoritative facts, [NOTE] for context, [BUG] for known failures, [?] for
  unverified — plus an AI manifest at the top that tells the model what to read and skip. No tooling, just annotation.

  In practice it cut per-query token load ~70% on our longer docs. Small models (7B) handle it well because the tags
  remove the structural reasoning problem entirely.

  Spec and examples: https://github.com/catcam/hads

bradystroud4 mesi fa

Its still very experimental - best thing to do is keep trying different things and see what sticks

There are great videos on Skills, Subagents etc. I'd give them a watch.

Context locality is a big one https://bradystroud.dev/blogs/context-locality

Heres another tip https://bradystroud.dev/blogs/show-ai-the-bug

sathishmg4 mesi fa