Slopfix charges $10,000 a week to delete AI-generated code bloat using AI agents

'Slopfix' software team charges $10,000 a week to delete AI-generated code bloat -- ironically, the team uses AI agents to trim messy repositories by up to 65%

A software house (if you can call it that) known as 'Slopfix' has launched a fixed-price service that refactors AI-generated codebases, charging $10,000 for one week of work and getting paid according to how much code it deletes. Its three engineers agree to a line-reduction target before starting, with a stated example of whittling a 100,000-line project down to 35,000 while maintaining the same functionality. The best part? Slopfix uses AI coding agents itself to do the trimming. According to its website, Slopfix analyzes its clients' repos for free and walks away if it decides it can't make a dent. When it does take a job, the first step is a written inventory of what the application does, screen by screen and endpoint by endpoint, effectively doubling as a regression checklist before any changes are made. Clients keep the slimmed-down codebase, that checklist, and a set of guardrails meant to slow future bloat, including a CLAUDE.md instruction file, lint rules, and CI checks. A two-week warranty covers any issues that arise from a previously working component. The company's founder, who posts on Hacker News as 'zie1ony,' wrote in the launch thread that Slopfix commits to a reduction target and the client pays in proportion to how much of it the team hits, adding that "we get paid to delete code." The engineers lean on coding agents to find and collapse redundancy, describing the tools as a power source kept "on a very short leash" rather than the thing making the calls. Duplicated code blocks are now appearing at the highest rate code-analytics firm GitClear has recorded across 623 million changes, up 81% since 2023, per the company's 2026 Maintainability Gap report. Refactoring has cratered over the same window, making up 21% of changed lines in 2022 and sits below 4% so far in 2026. Developers are now roughly five times more likely to copy and paste than to refactor, a reversal from 2022. With AI-generated "vibe-coded" code, issues tend to start showing up several months into a project once agents stop holding the whole context of the codebase in their immediate memory and begin reinventing logic. It's the same failure mode behind the vibe-coded OS that scored five out of nine on a basic functionality test earlier this year, and the unsupervised setup that let a coding agent wipe a company's production database in seconds. Slopfix's business model isn't anything new. Decades ago, consultancies built businesses untangling offshore-outsourced code, then cloud migrations, then crypto integrations. AI-generated code is just the latest iteration of that, but it's accumulating faster than any of those, meaning Slopfix can charge a serious premium for its services. That said, it simply undoes agentic output with the same class of agent that produced it in the first place, and anyone who has spent any time on the Internet recently will immediately flag the marketing copy on its own landing page as the type of AI slop it promises to clear out -- naturally. Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

'Slopfix': A software team is charging up to $10,000 to clean up AI-generated code, with the help of *checks notes* AI

AI slop. If you've heard the term, there's a good chance you are similarly exasperated with the onslaught of low-quality, AI-generated... well, slop. One team is now charging up to $10,000 per project to try and cut down AI-generated slop code and is, rather ironically, using AI to do it. As reported by Tom's Hardware, the team is called Slopfix, and their aim is to cut down unnecessary AI-generated code by a certain amount, taking a percentage of the $10,000 fee depending on how much of the target they hit. The example given on their website is to cut down 100,000 lines to 35,000. This means, if they remove 65,000 lines, they would claim $10,000. If, however, they managed to cut it down by 32,500 lines, they would instead get $5,000. The tool they use? Claude Code. But the team says they keep it "on a very short leash". The team of three claims to have "thirty years of combined experience about what maintainable code looks like" and says "the agent doesn't get a vote." One of the biggest problems with vibe coding is not the eventual output, but that building on that codebase can be unstable. AI agents tend to produce the favoured output, but can't 'think' about the next steps, so AI code is often filled with duplications and inefficiencies, hence "AI slop". This is a pretty common problem right now. Just a few months ago, the team behind a popular PS3 emulator asked users to stop "submitting AI slop code", and open-source game engine Godot was drowning in AI slop code at the start of the year. Just last month, Godot stopped accepting AI-generated code contributions as it couldn't "trust heavy users of AI to understand their code enough to fix it". Cleaning up AI code doesn't fix problems with users not understanding their output, but it could make it easier for AI agents to build on. Whether or not clients will want to pay tens of thousands of dollars for a different team to use the same tools as them to clean up their codebase is anyone's guess, though. I, for one, am sceptical of whether or not the Slopfix website is human-made, and the text on the site doesn't give me the greatest confidence. Still, one question sits in my mind. If those prompting AI-generated code are paying AI agents to fix up its mistakes, who makes sure that those AI agents are acting efficiently? And if the three engineers behind Slopfix are manually going through the code, what's the point of the coding bots in the first place?