Our take
Newless than six months old and changing fast- Activity
- 77
- Community
- 40
- Issues
- 75
- Pull requests
- 51
- Releases more often than 86% of the projects we track
anti-slop is an actively maintained, narrowly focused set of agent rules, but its recent pace and contributor concentration make it worth evaluating in your own agent workflow before relying on it broadly.
Good fit if
- You use one of its supported coding agents and want reusable rules for filtering generic AI output across UI, writing, accessibility, mobile layout, or code comments.
- You can provide design direction in DESIGN.md for UI work rather than expecting the rules to invent a visual identity.
- You want a project with frequent recent releases and quick issue and pull request handling, and are comfortable with most contributions coming from one person.
Look elsewhere if
- You need a tool that generates a complete visual direction or style guide rather than filtering undesirable patterns.
- Your coding agent is not among the supported agents, or your team does not want to install and maintain agent skills.
- You require a project with a longer operating history or more distributed contributor ownership.
All health signals
| Last commit | 2026-11-13 (3 days ago) |
|---|---|
| Commits, last 90 days | 97 |
| Releases, last 12 months | 48 (latest v3.2.30, 2026-11-13) |
| Contributors | 12 (top contributor: 77% of commits) |
| Issues closed, last 90 days | 14 (typically closed in 1 day) |
| Pull requests merged, last 90 days | 27 (typically merged in 1 day) |
| Project age | 3 months |
Checked on 2026-11-16 with the GitHub API.
Overview
anti-slop is a rulebook distributed as agent skills for AI coding agents. Its core filter aims to catch generic AI-generated UI, text, and code without prescribing colors, fonts, or layouts; the project describes itself as a filter, not a style guide. It supports agents including Claude Code, Codex, Cursor, Cline, and others, with an installer for selecting skills and installation locations.
The core rules apply across tasks, while separate skills cover UI work, copywriting, accessibility, mobile layouts, and code comments. For UI intended to ship, the project says a DESIGN.md must provide visual direction: anti-slop removes unwanted patterns but does not create a design direction on its own.
Key Features
- Core rules for filtering generic patterns in AI-generated work, with a Delivery Gate report.
- Six skills: a core filter plus focused skills for UI, copywriting, accessibility, mobile layouts, and code comments.
- During mode guides work as it is built; After mode audits existing work and presents findings for approval.
- An installer lets users choose skills, installation scope, and supported coding agents.
- Plugin and skill installation routes for a range of agents, including Claude Code, Codex, Cursor, and Cline.
- A standalone
antislop.mdfile can be downloaded for use in a chat without installing skills.
Use Cases
- A frontend developer wants an AI agent to avoid familiar generic landing-page patterns while following a project-specific
DESIGN.md. - A writer uses an agent to revise launch copy and wants it to flag hype, empty claims, and generic phrasing.
- A team reviews an existing interface for accessibility and mobile layout issues using the focused audit skills.
- A developer asks an agent to clean up AI-shaped code comments without removing comments that convey useful information.
What you need
Detected in the repository
- Node.js (from package.json)
- Automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
The recommended installer requires Node.js 20.12 or later:
npx antislop-ai
Choose skills, installation scope, and agents when prompted. See the README and installation guide for agent-specific options and update instructions.
Considerations
- The project is new and changing quickly. Its recent development and release activity is strong, but it has a short history to assess.
- Contributor activity is concentrated in one person, which is a continuity risk despite contributions from others.
- The repository reports no test suite. Teams should validate the rules and installer behavior in their own environments.
- Anti-slop is not a substitute for design decisions. The project requires
DESIGN.mdfor UI work intended to ship and explicitly does not promise to beautify output by itself. - The installer needs Node.js 20.12 or later. The repository is MIT-licensed, so review the license terms when incorporating or redistributing it.
Found this useful?
Share it with someone who would like anti-slop.