Add agents.txt v1.0 at repo root#58801
Open
barneywohl wants to merge 1 commit into
Open
Conversation
barneywohl
pushed a commit
to barneywohl/agentpress
that referenced
this pull request
May 13, 2026
…ypescript}, claude-code - modelcontextprotocol/servers#4154 - anthropics/anthropic-sdk-python#1539 - anthropics/anthropic-sdk-typescript#1043 - anthropics/claude-code#58801 All 5 friendly-seed PRs (per LAUNCH/TARGET_REPOS.md tier 1) now filed. Holding off on the 15 secondary targets per maintainer guidance: filing more in one day from the same account would look bot-shaped.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds agents.txt to declare what AI agents may do on this repo
Honest opener: this PR, and the
agents.txtv1.0 spec it implements, were built entirely with Claude Code in autonomous/goalmode by a heavy daily user. So Claude Code is, in a real sense, the first author and the first target.What is agents.txt
A small INI file at the repo root that tells autonomous coding agents what's allowed, what's prohibited, and what needs human approval. Same lineage as
robots.txt → sitemap.xml → llms.txt → agents.txt. Spec v1.0 shipped this week:https://github.com/barneywohl/agentpress/blob/main/docs/AGENTSTXT_SPEC.md
Why this repo specifically
The companion tool
agentpressships an MCP server that explicitly targets Claude Code (its README has a "Wire into Claude Code" section: https://github.com/barneywohl/agentpress). If Claude Code natively respectedagents.txt, every Claude Code user would get a free policy-aware layer on every repo they touch — agentpress or not. Adopting it here is the highest-leverage signal in the ecosystem.What this adds
agents.txtat the repo rootprohibited_actionscovers anything that could affect the binary's reputation (npm publish, install script edits, force push, impersonation)requires_human_approvalcovers README, SECURITY.md, LICENSE, CHANGELOG, scripts/, workflows/, issue templates, plugins/, examples/entry_pointsmap to the real issue templates (bug_report.yml,feature_request.yml,documentation.yml,model_behavior.yml)What this does NOT do
CLA
Happy to sign Anthropic's CLA / acknowledge Commercial ToS as needed. Flag me and I'll complete it before review.
Stakes
This is the most visible PR of the agents.txt launch wave and I want it to land cleanly, not be a stunt. Fully understand if the answer is "interesting, but not yet" — happy to close if not a fit. Either way, thank you for what you've built; this PR exists because Claude Code made building agents.txt possible.
— filed by an active Claude Code user