I used autoresearch to improve my AGENTS.md, measured against real tasks
The author utilized Codex to improve their AGENTS.md through iterative testing against real tasks. Despite initial improvements, the final version showed regression on a clean holdout, indicating that blindly implementing changes could be detrimental. The process highlighted the importance of treating AGENTS.md as a critical component of coding systems rather than just documentation.
- ▪Codex iterated on AGENTS.md eight times, measuring each version against real pull requests.
- ▪The best iteration improved some metrics but regressed on a clean holdout, indicating potential risks in blindly shipping changes.
- ▪The methodology involved evaluating various aspects such as correctness, maintainability, and footprint risk.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Stet |
| Canonical URL | https://www.stet.sh/blog/how-i-used-codex-to-improve-its-own-agents-md |
| Publication time | Wed, 27 May 2026 19:56:09 +0000 |
| Retrieval time | 2026-05-27T20:08:04.392Z |
| Last seen | 2026-05-27T20:08:04.392Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | zEU7nG2et_nB |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
I had Codex iterate on its own AGENTS.md 8 times and measured each version against real PRs. The best one still regressed on a clean holdout.May 27, 2026resultsmethodologyprocesstracing behaviorwhere I landedtakeaway I have a confession: I vibe-coded my AGENTS.md, and I'm pretty sure it's slop. I needed to make it better. Naturally, I asked Codex to do it. The difference: this time, Codex used a benchmark on my repo to measure each change, and optimized AGENTS.md against the data, instead of on pure vibes. Why We Should Take AGENTS.md Seriously Saying "AGENTS.md is important" is, at this point, a cliche. At risk of beating a dead horse, I'll say it again. Someone adds a rule that sounds smart, senior, and reasonable, commits it, and hopes the agent behaves better.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Stet.
Discussion
0 commentsMore from Stet
