Show HN: I got tired of syncing Claude/Gemini/AGENTS.md and .cursorrules

Re:Show HN: I got tired of syncing Claude/Gemini/AGENTS.md a... by wolfejam on Friday February 27, 2026 @02:12PM (#47184338)

ln -s makes all four files identical. Whichever format you write it in, the other three get the wrong structure. This generates each in its native format.

[ Parent | on HN ]

Re:Show HN: I got tired of syncing Claude/Gemini/AGENTS.md a... by verdverm on Friday February 27, 2026 @02:13PM (#47184352)

show me good evals that it actually makes a difference

that is the opposite of what I see

[ Parent | on HN ]

Re:Show HN: I got tired of syncing Claude/Gemini/AGENTS.md a... by wolfejam on Friday February 27, 2026 @02:21PM (#47184422)

ETH Zurich tested this: LLM-generated prose context = -3% performance, +20% cost. Even human-written = +4% at +19% cost. The problem is prose bloat. Structured formats avoid that by design. https://arxiv.org/abs/2602.11988

[ Parent | on HN ]

Re:Show HN: I got tired of syncing Claude/Gemini/AGENTS.md a... by verdverm on Friday February 27, 2026 @04:13PM (#47185693)

There is research that shows the opposite. A literature survey will show you something different than a single paper.

[ Parent | on HN ]

Re:Show HN: I got tired of syncing Claude/Gemini/AGENTS.md a... by wolfejam on Saturday February 28, 2026 @11:05AM (#47196926)

ETH Zurich studied 5,694 PRs across 12 diverse repos.

[ Parent | on HN ]