> ## Content Index > Fetch the complete content index at: https://www.notatechguy.com/llms.txt > Use this file to discover other available public pages before exploring further. # Impeccable hits 99,000 GitHub stars catching AI design slop with zero - URL: https://www.notatechguy.com/impeccable-hits-99-000-github-stars-catching-ai-design-slop-with-zero-llms/ - Published: 2026-11-02T00:48:23.000Z - Updated: 2026-11-02T00:48:24.000Z - Description: Impeccable, a Rust-based open-source tool, uses 62 deterministic rules to catch AI coding agents' design mistakes before they ship. - Author: Marcello Babbili - Tags: Technology & AI, AI Models, Anthropic Developer pbakaus pushed the Impeccable repository past 99,311 GitHub stars today, adding 1,140 in a single day to reach GitHub's daily trending list [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). The Rust-based linter targets design mistakes that AI coding agents leave behind — what the README labels "AI slop", using 62 deterministic rules rather than a language model or API key [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). That runs against the grain of a market where the default fix for bad AI output is another AI layer. **My read:** The appeal is obvious: a rule-based linter for design quality costs nothing to run and adds no latency. But the 62-rule count and the broad compatibility claim across 20-plus agents are both self-reported by the maintainer — no independent audit has been published, no error bars or test suites are available, and the star count is GitHub's own metric with no verification of unique users [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). The Fable 5.1 before-and-after comparison in the README is a marketing example the maintainer chose, not a benchmark. The number I would watch is whether the rules hold up against real agent output from tools like Cursor or Claude Code, not the curated demo. ### Impeccable ships 24 commands and two context files Impeccable installs via `npx impeccable install` from a project root, then runs `/impeccable init` inside a coding agent [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). It writes a PRODUCT.md file to capture project context and can snapshot an existing visual system into DESIGN.md [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). From there, 24 commands steer the agent's output: `polish` and `bolder` push designs in specific directions, `critique` scores the design, `audit` checks accessibility, `distill` strips what the page doesn't need [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). The compatibility list is long: Claude Code, Cursor, Codex CLI, GitHub Copilot, Devin, Replit Agent, Gemini CLI, and more than a dozen others [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). The latest release, skill-v4.8.0 on 26 October, added Devin and Replit Agent support and accepts `windsurf` as an alias [P⁴](https://github.com/pbakaus/impeccable/releases?ref=notatechguy.com). None of these integrations have been independently verified — the claims rest on the maintainer's own testing, with no released test harness or third-party reproduction. ### Deterministic rules cost zero inference and no API dependency The tool's core bet is that AI-generated interfaces have tells: cramped padding, skipped headings, generic colour palettes. Sixty-two deterministic rules flag those patterns directly, without calling a model [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). That means zero inference cost and no dependency on an API that could rate-limit or change pricing. This lands at a moment when coding agent adoption is accelerating. Cline, an open-source coding agent, hit 70,000 GitHub stars last month, and enterprises are routing agent traffic across models to cut spend. A design-quality linter that runs locally in Rust [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com) fits the same cost-conscious pattern. A frontend engineer running Cursor or Claude Code could install Impeccable, run `audit` on generated components, and get a rules-based pass on accessibility and spacing before code reaches review — the tool flags missing heading hierarchy or tight padding without a second model call, so the engineer's review queue shrinks by one automated pass per component [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). Whether the 62 rules cover enough ground to catch real-world slop, or just the curated examples in the README, is the open question. The Neo Mirai case study and the Fable 5.1 comparison are maintainer-selected examples, not independent evaluations [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). Full documentation is hosted at impeccable.style/docs [S¹](https://github.com/pbakaus/impeccable?ref=notatechguy.com). The skill-v4.8.0 release on 26 October is the latest checkpoint [P⁴](https://github.com/pbakaus/impeccable/releases?ref=notatechguy.com). --- *Sources: [S1 — pbakaus/impeccable: The design vocabulary for your coding agent. Steer](https://github.com/pbakaus/impeccable?ref=notatechguy.com) · [P2 — README.md](https://github.com/pbakaus/impeccable/blob/master/README.md?ref=notatechguy.com) · [P3 — narunraman/STEER](https://github.com/narunraman/steer?ref=notatechguy.com) · [P4 — Releases · pbakaus/impeccable · GitHub](https://github.com/pbakaus/impeccable/releases?ref=notatechguy.com) · [P5 — huggingface/faq](https://github.com/huggingface/faq?ref=notatechguy.com)* --- *Written from 5 sourced items, 4 of them primary.* ![Impeccable at a glance](https://storage.ghost.io/c/6e/89/6e896869-22ef-4281-a213-b4c462c17cff/content/images/2026/11/chart_9a69d4dd12cee6febcb3.png) ## More from Not A Tech Guy - [Screenpipe records your desktop to feed AI agents, hits 22,000 stars](https://www.notatechguy.com/screenpipe-records-your-desktop-to-feed-ai-agents-hits-22-000-stars/) - [Locally Uncensored app trends on GitHub with 3,046 stars](https://www.notatechguy.com/locally-uncensored-app-trends-on-github-with-3-046-stars/) - [OpenMontage AI video agent hits 74,000 GitHub stars](https://www.notatechguy.com/openmontage-ai-video-agent-hits-74-000-github-stars/)