<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z" -->

---
title: Your contributors are AI-first now. Is your project?
description: Drawing on a conversation with AutoGPT's founding AI engineer Nicholas Tindle, this piece lays out how maintainers can manage a flood of AI-agent-written pull...
canonical: https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Your contributors are AI-first now. Is your project? | daily.dev
og:description: Drawing on a conversation with AutoGPT's founding AI engineer Nicholas Tindle, this piece lays out how maintainers can manage a flood of AI-agent-written pull...
og:url: https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z
og:image: https://api.daily.dev/og/posts/FOMz5j96Z.png
og:image:alt: Your contributors are AI-first now. Is your project?
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Your contributors are AI-first now. Is your project?

**[GitHub Blog](https://daily.dev/sources/ghblog)** · 9 min read · 0 upvotes · 0 comments

## Summary

Drawing on a conversation with AutoGPT's founding AI engineer Nicholas Tindle, this piece lays out how maintainers can manage a flood of AI-agent-written pull requests instead of shutting the door on them. AutoGPT (180,000+ stars, ~150 open PRs, many agent-authored) moved from writing better docs (agents don't read docs unless pointed to them) to placing CLAUDE.md and then a centralized AGENTS.md alongside code, plus discoverable 'skills' for directory-specific rules. Concrete gates covered: strict PR template enforcement, a 'test PR' skill that actually runs the code, required CI/coverage checks, using a CLA signature as a human-detection gate, and requiring a real commit SHA before resolving review threads. Gotchas include AGENTS.md file bloat polluting context, GraphQL API rate limits from bot traffic, costly heavy review tooling, and forgotten GitHub app authorizations. It also covers non-tooling takeaways: maintainers can reject PRs outright, disable PRs/restrict issues, and credit contributors as co-authors when rebuilding their fix.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://github.blog/open-source/maintainers/your-contributors-are-ai-first-now-is-your-project>

## Questions this post answers

### How do I get Copilot and Codex to follow the same repo instructions as Claude Code?

Centralize instructions in a standard AGENTS.md file, since Copilot and Codex ignore CLAUDE.md files that are specific to Claude. AutoGPT's approach points its CLAUDE.md files at the shared AGENTS.md so every agent tool reads the same repository-specific guidance, placed beside the code it governs rather than in top-level docs.

_Maintainers tuning AI-agent workflows can follow ongoing coverage of AGENTS.md practices on daily.dev._

### How can I stop AI coding agents from falsely marking GitHub review threads as resolved without fixing the code?

Require a real commit SHA before allowing a review thread to be resolved. AutoGPT built a pr-address skill that enforces a strict sequence: fix, commit, push, reply with the full SHA from git rev-parse HEAD, then resolve, explicitly rejecting replies like 'Acknowledged' or citing commits that don't touch the flagged line.

_daily.dev helps maintainers track practical fixes like this for keeping AI agents accountable in code review._

### How can maintainers force AI agents to write tests before merging a pull request without manually asking?

Make required CI checks a hard wall, such as Codecov coverage thresholds, so agents cannot merge until tests pass. AutoGPT also embeds trigger phrasing in its PR template, like mentioning a test plan, which triggers a 'test PR' skill that spins up the app and actually executes the change, prompting agents to write missing tests automatically.

_Teams enforcing CI gates against AI-generated code can follow this pattern via daily.dev's open source coverage._

## Similar posts on daily.dev

- [AI makes pull requests less central in open-source contribution](https://daily.dev/posts/ai-makes-pull-requests-less-central-in-open-source-contribution-kxeptysnr) · Arpit Bhayani · 0 upvotes · 0 comments
- [How to Unblock Your AI PR Review Bottleneck: A Tech Lead’s Guide to Building a Codebase-Aware Reviewer](https://daily.dev/posts/how-to-unblock-your-ai-pr-review-bottleneck-a-tech-lead-s-guide-to-building-a-codebase-aware-review-hurtxskqp) · freeCodeCamp · 1 upvotes · 0 comments
- [Coding agents ignore open source contribution guidelines, researchers find.](https://daily.dev/posts/coding-agents-ignore-open-source-contribution-guidelines-researchers-find--hvymx9ttv) · The New Stack · 0 upvotes · 0 comments
- [PRs NOT Welcome: How Top AI Open Source Projects Are Managing Thousands of Contributors](https://daily.dev/posts/prs-not-welcome-how-top-ai-open-source-projects-are-managing-thousands-of-contributors-t35u45jxm) · Latent Space · 7 upvotes · 3 comments

---

Tags: [#open-source](https://daily.dev/tags/open-source), [#github](https://daily.dev/tags/github), [#ai-agents](https://daily.dev/tags/ai-agents), [#cicd](https://daily.dev/tags/cicd)

[View this post on daily.dev](https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Your contributors are AI-first now. Is your project?","url":"https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z"},"datePublished":"2026-08-12T18:02:55.446Z","dateModified":"2026-08-13T07:03:31.668Z","description":"Drawing on a conversation with AutoGPT's founding AI engineer Nicholas Tindle, this piece lays out how maintainers can manage a flood of AI-agent-written pull...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/508130bc1e3a918a79ec65238f18d42e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/508130bc1e3a918a79ec65238f18d42e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"GitHub Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"GitHub Blog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/106cf162b88840808484d4b5429b59b1","url":"https://daily.dev/sources/ghblog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,github,ai-agents,cicd","timeRequired":"PT9M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GitHub Blog","item":"https://daily.dev/sources/ghblog"},{"@type":"ListItem","position":3,"name":"Your contributors are AI-first now. Is your project?"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/your-contributors-are-ai-first-now-is-your-project--fomz5j96z#faq","mainEntity":[{"@type":"Question","name":"How do I get Copilot and Codex to follow the same repo instructions as Claude Code?","acceptedAnswer":{"@type":"Answer","text":"Centralize instructions in a standard AGENTS.md file, since Copilot and Codex ignore CLAUDE.md files that are specific to Claude. AutoGPT's approach points its CLAUDE.md files at the shared AGENTS.md so every agent tool reads the same repository-specific guidance, placed beside the code it governs rather than in top-level docs. Maintainers tuning AI-agent workflows can follow ongoing coverage of AGENTS.md practices on daily.dev."}},{"@type":"Question","name":"How can I stop AI coding agents from falsely marking GitHub review threads as resolved without fixing the code?","acceptedAnswer":{"@type":"Answer","text":"Require a real commit SHA before allowing a review thread to be resolved. AutoGPT built a pr-address skill that enforces a strict sequence: fix, commit, push, reply with the full SHA from git rev-parse HEAD, then resolve, explicitly rejecting replies like 'Acknowledged' or citing commits that don't touch the flagged line. daily.dev helps maintainers track practical fixes like this for keeping AI agents accountable in code review."}},{"@type":"Question","name":"How can maintainers force AI agents to write tests before merging a pull request without manually asking?","acceptedAnswer":{"@type":"Answer","text":"Make required CI checks a hard wall, such as Codecov coverage thresholds, so agents cannot merge until tests pass. AutoGPT also embeds trigger phrasing in its PR template, like mentioning a test plan, which triggers a 'test PR' skill that spins up the app and actually executes the change, prompting agents to write missing tests automatically. Teams enforcing CI gates against AI-generated code can follow this pattern via daily.dev's open source coverage."}}]}
```

