Show HN: Turn .cursorrules / repo guidelines into GitHub pre-merge checks (OSS)(watchflow.dev)
watchflow.dev
Show HN: Turn .cursorrules / repo guidelines into GitHub pre-merge checks (OSS)
https://watchflow.dev
Building an open-source repo with deterministic validators backed by agent evaluation loops to turn agent instructions (.e.g. .cursorrules, claude-guidelines.md, copilot-prompts.md) into hard guarantees.
10 comments
Hi HN!
Maintainers are increasingly dealing with large volumes of low-context PRs, especially as AI coding tools make it easier to generate changes without the surrounding intent.
Many repos already define contribution expectations in places like .cursorrules, CONTRIBUTING.md, or internal guidelines but those rules rarely translate into something enforceable during review.
We built Watchflow to bridge that gap: an open-source GitHub check that translates repository guidelines into enforceable validation logic that runs on every PR.
The model is intentionally hybrid:
- ~95% deterministic validators (fast, predictable, pure Python)
- Optional LLM checks for semantic cases like description / diff alignment
- LLM layer fails open so merges never block on model issues
Example rules:
- Require a linked issue
- Require CODEOWNERS review
- Block PRs above a LOC threshold
- Ensure PR descriptions align with code changes
- Validate contribution patterns defined in .cursorrules or agent guidelines
The goal is to close the loop between repository intent -> code diff -> enforceable governance.
Repo: https://github.com/warestack/watchflow
If there are review patterns you’re seeing that aren’t covered yet, happy to turn them into new validators!
Maintainers are increasingly dealing with large volumes of low-context PRs, especially as AI coding tools make it easier to generate changes without the surrounding intent.
Many repos already define contribution expectations in places like .cursorrules, CONTRIBUTING.md, or internal guidelines but those rules rarely translate into something enforceable during review.
We built Watchflow to bridge that gap: an open-source GitHub check that translates repository guidelines into enforceable validation logic that runs on every PR.
The model is intentionally hybrid:
- ~95% deterministic validators (fast, predictable, pure Python)
- Optional LLM checks for semantic cases like description / diff alignment
- LLM layer fails open so merges never block on model issues
Example rules:
- Require a linked issue
- Require CODEOWNERS review
- Block PRs above a LOC threshold
- Ensure PR descriptions align with code changes
- Validate contribution patterns defined in .cursorrules or agent guidelines
The goal is to close the loop between repository intent -> code diff -> enforceable governance.
Repo: https://github.com/warestack/watchflow
If there are review patterns you’re seeing that aren’t covered yet, happy to turn them into new validators!
This is a great approach - catching rule violations before merge rather than relying on developers to remember them. The biggest challenge with .cursorrules adoption at scale is consistency across repos.
I maintain a collection of .cursorrules for 16+ frameworks (React, Next.js, FastAPI, Go, etc.) that could work as a baseline for these kinds of checks: https://github.com/survivorforge/cursor-rules
Curious how you handle framework-specific rules that only apply to certain parts of a monorepo?
I maintain a collection of .cursorrules for 16+ frameworks (React, Next.js, FastAPI, Go, etc.) that could work as a baseline for these kinds of checks: https://github.com/survivorforge/cursor-rules
Curious how you handle framework-specific rules that only apply to certain parts of a monorepo?
Great stuff, I just had a look at the langchain-ai, nextjs, and tailwindcss rulesets. I'll try them out in our internal repos.
As for your question, the evaluation loop has access to the PR diff and can identify the file paths affected by the change. Each rule in rules.yaml can specify a path or scope, so framework-specific checks only trigger when the relevant parts of the monorepo are touched.
As for your question, the evaluation loop has access to the PR diff and can identify the file paths affected by the change. Each rule in rules.yaml can specify a path or scope, so framework-specific checks only trigger when the relevant parts of the monorepo are touched.
Is it free for open-source repos? It could be really useful to lower the noise from new contributors not following contribution guidelines.
There is a preview environment that is currently free for both private and public repositories (at least for now). Early access also helps us expand the rule set and harden the core engine.
Is it self-hostable for private repos?
Yes, both public and private. There is a guide with instructions in the repo.
Looks like it, tried it on my vibe-coded project, looks pretty good so far.