Ship vibe-coded apps with confidence
Joined June 2026
- Tweets16
- Following2
- Followers13
- Likes69
CleanSlop retweeted
Congrats Swaroop and team! Excited to see how the trusted identity @stripe 's @link provides to agents helps conversion!
I've been teasing this for a while, and I'm really excited to finally ship it: CleanSlop is now fully agentic 🔥
Paste one line into Claude Code, Codex, Cursor, Grok Bot or Muse 👇
Scan with cleanslop.com
This is a big step up from our first release last month. Back then @CleanSlop was a website: you'd leave your agent to sign up, connect GitHub, run a scan and read the report, then paste it all back in. Now the whole thing happens inside your agent, with a leaner workflow and an overhauled, faster engine underneath.
Your agent signs you in, scans the folder you're in, fixes what's worth fixing, and rescans to check the fixes held. When you run out of scans, it offers a pack or a plan, and you approve it in Link. That's the only time you touch anything.
All of this is backed by @link Agent Identity, @stripe's new identity product for agents, and we're one of the first companies to integrate it across the entire workflow. Your agent presents Link's attestation that a real person stands behind it, along with your Link-verified email, right from the CLI. There's no form, no password and no trip to a website.
It supports TypeScript/Node.js apps today, and it's sharpest on Next.js + Supabase. Link Agent Identity is US and Canada only for now; everywhere else, your agent signs in with GitHub.
We're on @ProductHunt today. If you build with AI, I'd love for you to try it and tell me where it gets confusing or where your agent gets stuck 🙏
CleanSlop retweeted
The heady mix of exhaustion and accomplishment is real today. The second major, 100% agentic, release of @CleanSlop is on Product Hunt today. It supports Stripe's @Link agent identity to attest to the validity of an agent. We are among the first few products at the moment to integrate it throughout our workflow. And cleanslop.com is a first-class agentic resource at this point. Just point your agent or assistant to it in the context of the codebase you want to work on.
Also, definitely a good time to clear out recurring queries and refrains that we keep running into. (blogs and docs will be up once the dust settles from handling the influx from this release)
- This is a deterministic risk scanning and surfacing engine that has been trained on 25+ categories of where and when things can go wrong. How do we know where to look? Just check the scale of things we have worked on in the last decade.
- Techincally, it is static analysis. We haven't gotten to the runtime yet. And it is currently monofocussed on vibecoded webapps that are typically generated on Next.js/TS/Supabase sort of stack. iOS support coming soon.
- The engine is continually trained, updated and refined on widely available public corpora of codebases as well as synthetically generated ones. We can promise our results and findings will only get better with time, not regress.
- WE ARE NOT A LLM WRAPPER AND YOUR CODE DOES NOT GET SHIPPED TO RANDOM LLM PROVIDERS. Can not stress this enough. We have a ZDR in place if you don't want to include your codebase for training purposes, and when it comes to multi-phased scans where the scanner surfaces findings it is not confident on, only slices of callgraphs, import trees etc are consulted with decision models like @typesafeai Jev or @Cloudflare Clef.
- This is NOT a security audit. This is not a package or collection of SKILL.md files that require an LLM subscription from you. This is definitely something that will bring to attention what will break when internet scale traffic and users hit your app.
I've been teasing this for a while, and I'm really excited to finally ship it: CleanSlop is now fully agentic 🔥
Paste one line into Claude Code, Codex, Cursor, Grok Bot or Muse 👇
Scan with cleanslop.com
This is a big step up from our first release last month. Back then @CleanSlop was a website: you'd leave your agent to sign up, connect GitHub, run a scan and read the report, then paste it all back in. Now the whole thing happens inside your agent, with a leaner workflow and an overhauled, faster engine underneath.
Your agent signs you in, scans the folder you're in, fixes what's worth fixing, and rescans to check the fixes held. When you run out of scans, it offers a pack or a plan, and you approve it in Link. That's the only time you touch anything.
All of this is backed by @link Agent Identity, @stripe's new identity product for agents, and we're one of the first companies to integrate it across the entire workflow. Your agent presents Link's attestation that a real person stands behind it, along with your Link-verified email, right from the CLI. There's no form, no password and no trip to a website.
It supports TypeScript/Node.js apps today, and it's sharpest on Next.js + Supabase. Link Agent Identity is US and Canada only for now; everywhere else, your agent signs in with GitHub.
We're on @ProductHunt today. If you build with AI, I'd love for you to try it and tell me where it gets confusing or where your agent gets stuck 🙏
CleanSlop retweeted
I've been teasing this for a while, and I'm really excited to finally ship it: CleanSlop is now fully agentic 🔥
Paste one line into Claude Code, Codex, Cursor, Grok Bot or Muse 👇
Scan with cleanslop.com
This is a big step up from our first release last month. Back then @CleanSlop was a website: you'd leave your agent to sign up, connect GitHub, run a scan and read the report, then paste it all back in. Now the whole thing happens inside your agent, with a leaner workflow and an overhauled, faster engine underneath.
Your agent signs you in, scans the folder you're in, fixes what's worth fixing, and rescans to check the fixes held. When you run out of scans, it offers a pack or a plan, and you approve it in Link. That's the only time you touch anything.
All of this is backed by @link Agent Identity, @stripe's new identity product for agents, and we're one of the first companies to integrate it across the entire workflow. Your agent presents Link's attestation that a real person stands behind it, along with your Link-verified email, right from the CLI. There's no form, no password and no trip to a website.
It supports TypeScript/Node.js apps today, and it's sharpest on Next.js + Supabase. Link Agent Identity is US and Canada only for now; everywhere else, your agent signs in with GitHub.
We're on @ProductHunt today. If you build with AI, I'd love for you to try it and tell me where it gets confusing or where your agent gets stuck 🙏
CleanSlop retweeted
Just got our first paying subscriber for @CleanSlop :)
Launched 4 weeks ago today! Lean, bootstrapped, shipping weekly.
Can’t wait to share what we’re working on next week 👀
CleanSlop retweeted
Now live on prod for testing! Reply here or DM me if you want access :)
Connected @CleanSlop MCP live on call with @SwaroopH in Cursor IDE.
Frictionless application of changes in-editor.
Complete agentic support dropping this week for select beta users! DM us for early access.
CleanSlop retweeted
Last week we launched @CleanSlop. This week it got a proper front door :)
Here’s a 30s tour of the new site 👇
Plus, a special link for you in the thread 🧵
CleanSlop retweeted
I'm building a new company on a simple bet: AI will keep writing code faster than most teams can judge it.
@CleanSlop is our first product: it scans your repo and flags what breaks with real users.
Live on @ProductHunt today - would love your support 🙏
producthunt.com/products/cle…
CleanSlop retweeted
Code is moving faster than operational judgment.
@SwaroopH and I built @CleanSlop for vibecoded TypeScript apps to uncover production risks across data access, background jobs, external dependencies & scaling.
Today we launched @ProductHunt and would love some feedback.
👇 Link in 🧵