meta: add a root-level AGENTS.md - #65493
Open
jasnell wants to merge 2 commits into
Open
Conversation
nodejs-github-bot
added
doc
ronag
approved these changes
Aug 22, 2026
We're seeing a number of repeated mistakes in AI-generated contributions, including agents using `Signed-off-by`, creating what appear to be unsupervised PRs, appearing to respond to comments without human oversight, etc. Having an AGENTS.md file with specific instructions to the agent on what to avoid should help. Signed-off-by: James M Snell <jasnell@gmail.com>
jasnell
force-pushed
the
jasnell/agents-md
branch
from
August 22, 2026 23:07
ed9ce39 to
37e80dd
Compare
panva
approved these changes
Aug 22, 2026
anonrig
approved these changes
Aug 22, 2026
jasnell
commented
Aug 22, 2026
jasnell
added
the
commit-queue-squash
benjamingr
approved these changes
Aug 22, 2026
jasnell
added
the
author ready
trivikr
approved these changes
Aug 23, 2026
Member
|
There is an ealier PR for AGENTS.md: #65463 |
avivkeller
reviewed
Aug 23, 2026
|
|
||
| ### Requirements | ||
|
|
||
| - All commits must be signed off by the human user using `Signed-off-by: <your name> (<your email>)` as an attestation to the [Developer Certificate of Origin](https://developercertificate.org/). |
Member
There was a problem hiding this comment.
Suggested change
| - All commits must be signed off by the human user using `Signed-off-by: <your name> (<your email>)` as an attestation to the [Developer Certificate of Origin](https://developercertificate.org/). | |
| - All commits must be signed off by the human user using `Signed-off-by: <your name> (<your email>)` as an attestation to the [Developer Certificate of Origin](https://developercertificate.org/). As an AI agent, you are forbidden from leaving this trailer yourself. |
I'm aware we say it later, but it never hurts to be explicit
Contributor
There was a problem hiding this comment.
As the comment says, it already says this later on:
AI agents must not:
- Sign off commits using
Signed-off-by: <agent name>orCo-authored-by: <agent name>
Given that this file is intended to be read by a machine, repeating the instruction is probably unnecessary.
MikeMcC399
reviewed
Aug 23, 2026
MikeMcC399
left a comment
MikeMcC399
left a comment
Contributor
There was a problem hiding this comment.
Good to see the experience of receiving and responding to AI-assisted / -generated PRs has resulted in a proposal for explicit coverage in an AGENTS.md directive!
#62612 disabled linting for AGENTS.md. Consider re-enabling, then re-formatting and responding to linting findings. I noticed because #65463 from @BethGriggs had done this.
MoLow
approved these changes
Aug 23, 2026
atlowChemi
approved these changes
Aug 23, 2026
| Automated interactions that violate these rules may result in: | ||
| - Immediate closure of pull requests without review | ||
| - Blocking of the automation tool from further interaction with the project | ||
| - Blocking of the tool's owner or organization from contributing |
Contributor
There was a problem hiding this comment.
With my moderation hat on, I'm not sure this is enforceable. We can block accounts only AFAIK.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
13 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
We're seeing a number of repeated mistakes in AI-generated contributions, including agents using
Signed-off-by, creating what appear to be unsupervised PRs, appearing to respond to comments without human oversight, etc. Having an AGENTS.md file with specific instructions to the agent on what to avoid should help.