AGENTS.md
No written verdict yet. Here is what commenters said.
5recommend
2warn against
Dec 9, 2025first mention
Sep 19, 2026latest mention
Why people recommend it
“that has been AGENTS.md for a long while now”
“I stopped most spam with a simple AGENTS.md. It actually seems to work (for now).”
Show 3 more
“Agents.md actually scales and outperforms alternatives”
“I recently switched to using only AGENTS.md and SKILLS. I appreciate the standardization from this perspective.”
“The AGENTS.md approach provides broad, horizontal improvements”
Caveats and dissent
“The core issue isn't the idea of context files — it's that prose is the wrong format for structured facts.”
Often compared with
Who recommends it in their own words
Threads where it came up
- Agent Skills 2 mentions
- Claude Code now reads AGENTS.md if there is no Claude.md 1 mention
- We stopped AI bot spam in our GitHub repo using Git's –author flag 1 mention
- God Damn AI is making me dumb 1 mention
- Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML 1 mention
- Anthropic, Please Make a New Slack 1 mention
Data: agents-md.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 9
“that has been AGENTS.md for a long while now”
“I stopped most spam with a simple AGENTS.md. It actually seems to work (for now).”
“Most of my time goes into AGENTS.md, hooks, sub-agents, verification loops”
“Agents.md actually scales and outperforms alternatives”
Why on earth would Anthropic commit to interoperability? That is the company that doesn't interoperate with the standard LLM APIs that OpenAI developed, which everyone else in the industry has adopted and uses. Whether OpenAI's APIs are great or perfect or not, they are the standard that the industry has settled on. That is the same company that refuses to add support for AGENTS.md that everyone else in the industry
“The core issue isn't the idea of context files — it's that prose is the wrong format for structured facts.”
“I recently switched to using only AGENTS.md and SKILLS. I appreciate the standardization from this perspective.”
“The AGENTS.md approach provides broad, horizontal improvements”
“- AGENTS.md”