Anthropic implemented it https://github.com/Piebald-AI/tweakcc/pull/459
Where does your link say it’s Anthropic?
Feature Request: Support AGENTS.md
51–60 of 236 posts
Re: Feature Request: Support AGENTS.md
#52How exactly does Claude not support AGENTS.md? I can ask Claude to review AGENTS.md and it will read it. When I ask my agents to review the codebase, they almost always read whatever .md files exist.
Claude code will only read the other .md files after you take a turn to prompt it, not when the session starts. So if I run `/clear` it will retain the CLAUDE.md context but not AGENTS.md.
Re: Feature Request: Support AGENTS.md
#53Stop supporting Anthropic with your money. They are a hostile company.
Re: Feature Request: Support AGENTS.md
#54How exactly does Claude not support AGENTS.md? I can ask Claude to review AGENTS.md and it will read it. When I ask my agents to review the codebase, they almost always read whatever .md files exist.
You're asking the wrong question here. There is:
How exactly does Claude Code* not support AGENTS.md?
How exactly does the Claude suite of Models not support AGENTS.md?
The problem being pointed at in parent linked is referring to the Claude Code Harness not supporting AGENTS.md. Harnesses which do support it (eg codex), append the content to the initial model turn upon the model discovering it at the project root.
* Or Claude Code Tui, Claude Code desktop, Claude Cowork, Claude Desktop, Claude Design, Etc.
(Edit: i wish I could tattoo the distinction on ny forehead. Im vocal about Anthropic engineer-oriented tools being lackluster, and i frequently find myself in conversations where I have to stop a coworker and ask if they're talking about a platform, tool, or model- and which, depending on the answer. I feel like those two things together make me come off somewhat abrasive, but man, we're all engineers here.)
Re: Feature Request: Support AGENTS.md
#55Earlier quoted context omitted.
Claude Code is quickly becoming an anchor. Every week I marvel at how much worse it gets, how much more essential information is hidden and replaced with bloated useless TUI and rambling tangential responses that hide the useful bits of info behind jargon invented by the agent without ever explaining it to the user. It's like the PMs for Claude Code are reward hacking their own reinforcement learning.
What tools do you find are better? I have been happy with Claude Code lately, but I haven't explored other options much in over a year. Curious to try something else out if it's less rambling and tangential.
New guidelines that I have seen in a certain place is to configure and update existing CC setups to be CC/Codex agnostic. Plus setting up both allows Claude Code to delegate tasks [1] to Codex to reduce usage.
Most are easy to share with symlinks and @agents.
Re: Feature Request: Support AGENTS.md
#56Earlier quoted context omitted.
Claude Code is quickly becoming an anchor. Every week I marvel at how much worse it gets, how much more essential information is hidden and replaced with bloated useless TUI and rambling tangential responses that hide the useful bits of info behind jargon invented by the agent without ever explaining it to the user. It's like the PMs for Claude Code are reward hacking their own reinforcement learning.
What tools do you find are better? I have been happy with Claude Code lately, but I haven't explored other options much in over a year. Curious to try something else out if it's less rambling and tangential.
The sub only works in Claude Code itself (unless they changed that rule again?), and all the Chinese models are trained on Claude Code (a bunch of them don't even work in Codex).
I use a custom harness, but I constantly hear good things about Pi.
EDIT: Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism...
Mine's 50. (Lines.)
https://gist.github.com/a-n-d-a-i/bd50aaa4bdb15f9a4cc8176ee3...
Vendored in my own LLM micro library (100 LoC) so it's 150.[0]
There's no parallelism or anything, but I use it for surgical edits and it's much faster and cheaper than the official harnesses for some reason. (Absence of sysprompt bigger than my repo probably helps there...)
[0] This one uses OpenRouter so you can use it with any model, but jerry rigged Codex sub version available on demand :)
---
I also have a ultra turbo bloated version (500 lines... need to strip it down a bit!) which has autorun files (for grep-based context injection), notification (frog croak when agent done, etc.) Watch this space!
Re: Feature Request: Support AGENTS.md
#57Why not symlink AGENTS.md to CLAUD.md?
Re: Feature Request: Support AGENTS.md
#58Earlier quoted context omitted.
What tools do you find are better? I have been happy with Claude Code lately, but I haven't explored other options much in over a year. Curious to try something else out if it's less rambling and tangential.
New guidelines that I have seen in a certain place is to configure and update existing CC setups to be CC/Codex agnostic. Plus setting up both allows Claude Code to delegate tasks [1] to Codex to reduce usage. Most are easy to share with symlinks and @agents. https://github.com/openai/codex-plugin-cc
Oh my god, that's an official plugin. That's hilarious. I had the same idea last year, when I noticed how much cheaper GPT was for the same tasks, but Claude was still better as a high level "operator".
Also cause OpenAI was cool with you calling their sub in an automated way, but Anthropic very much was not (they were banning people at the time).
Re: Feature Request: Support AGENTS.md
#59Why not symlink AGENTS.md to CLAUD.md?
This is what I do. Works fine.
I’ll also include entries in the .github dir in project repos doing same thing in case anyone working on it happens to use GitHub copilot via vscode will also pick up on the AGENTS.md as well as any skills I might have cooked up for the repo.
(Though it’s mostly because I don’t trust team members to read the docs and the skills I made are meant to guide following standards for the project - and this approach almost incepts the standards for anyone not paying attention)
Re: Feature Request: Support AGENTS.md
#60The obvious reason is that they would prefer to have CLAUDE.md files in every repo (even if it's just a symlink to AGENTS.md). It serves as a free advertisement for them. Same reason as for auto-adding attribution text in commit messages, etc. It's the "Sent from my iPhone" of our time.
Except I actively despise that commit message anytime I see it.