My agent.md to improve LLM-assisted code quality

Fabien Sanglard · 21 Aug 2026

Fabien Sanglard did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
LLMs hallucinate constantly and cannot be trusted to produce code without human verification.

Their wordsLLMs constantly hallucinate and cannot be trusted. I still have to verify and iterate a lot but now I usually focus on architecture and design instead of code style.
Our reading
As an LLM's context grows, it pays less attention to instructions placed in the middle than to those at the start or end.

Their wordsAs the context grows, a model starts paying less attention to instructions in the middle of the context in favor of what is at the beginning and the end.

Keep reading

The other pieces are the ones whose claims are worded most like this one's. That measures language, not agreement: they may argue the opposite.