You've seen test-rot, specification rot, and documentation rot; we now introduce; prompt rot!
Cluttering the repo with out-dated, very wordy and quickly aging prompts will just confuse any agent tasked with looking at the repo in the future. Keeping context windows down is a real limitation to good LLM output, and this workflow may work completely against it.
- A plan.md describing the project, main abstraction idea, end costumer, and so on is great; but it should be kept minimal and up-to-date with the repo.
- Block comments on top of source-files and functions are great, and already very useful to coding agents. I don't see a value to anything more than what is already typical best practice.
For me they mostly append the end of the file with more sections or details. Heck it often adds very specific implementation details that it worked on recently that have no business being written in a repo wide summary.
Weird. I changed/amended model/integration and it updated table, provided explanation.
But yeah, I like to reference the docs so it can refresh his memory. But I may have had the .md files updated even if I didn't explicitly provide/ask for it, but a refactor that touched particular areas.
But yeah, my .md references others, it also maybe helps that my dir is named docs/ and it lists it somewhere in .md files... maybe its just the way it is structured helps infer agent what to do.
aDyslecticCrow · · focus · HN ↗
Cluttering the repo with out-dated, very wordy and quickly aging prompts will just confuse any agent tasked with looking at the repo in the future. Keeping context windows down is a real limitation to good LLM output, and this workflow may work completely against it.
- A plan.md describing the project, main abstraction idea, end costumer, and so on is great; but it should be kept minimal and up-to-date with the repo.
- Block comments on top of source-files and functions are great, and already very useful to coding agents. I don't see a value to anything more than what is already typical best practice.
jve · · focus · HN ↗
aDyslecticCrow · · focus · HN ↗
jve · · focus · HN ↗
But yeah, I like to reference the docs so it can refresh his memory. But I may have had the .md files updated even if I didn't explicitly provide/ask for it, but a refactor that touched particular areas.
But yeah, my .md references others, it also maybe helps that my dir is named docs/ and it lists it somewhere in .md files... maybe its just the way it is structured helps infer agent what to do.