Comment by aDyslecticCrow
6 hours ago
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.
I wonder if instead of checking the prompts into the repo as files, a better idea would be to store them inside the commit messages.
If prompts are specifications for a change of the system's behavior, then it seems natural to manage them as changes and not as resources.
This would also keep them in the right "historical context" of the repo and avoid the "prompt rot" you were talking about.
Git history is a bit annoying to navigate, but that may just be a tooling issue. I've long been bothered by the loss of the review history when merging a PR. Would actually be pretty cool to click on a row of code and see the commit messages that formed that row of code in a little sidebar, and the technical discussions that were behind it.
Functional safety development processes often demand code-review, technical design decisions, changes of plans, or intentional compromises; to be linked together with reference IDs in the code they effect. But the workflow for this is usually extremely manual and absolute misery. But a codebase made like this is like magic to read later.
Gits data structure already allows for that, as you can add additional data to a commit after it was made.
You'd consequently only need to implement your custom git gui and extension to visualize this information.
Maybe a good project for the next weekend? Just eg make a prototype tui in golang and see where you end up
I think the OP is referring to less transient use cases, like the actual source code to agent system instructions.
Already happens in my experience. I'll try to figure out why it keeps doing this one thing and it turns out it's from some poorly advised info it put in a markdown file 20 commits ago that CLAUDE.md or AGENTS.md tell it to treat as gospel.
Weekly reminder to delete your memories folder that claude code loves creating over the most silly of information.
"yes claude i prefered the blue graph two months ago, how does thar help us with this json parsing bug?"
I agree, because at the end of the day the source code is the source of truth and that's what the LLM should look at instead of some months old markdown file.