Back to search
sloplint
MarketplaceWorks with Claude CodeGitHub
Catch the checkable problems AI-written code ships with: hallucinated packages, placeholder code, tests that can't fail. CLI, GitHub Action and agent skills.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/talha-2--sloplint)HTML
<a href="/listings/talha-2--sloplint"><img src="/api/listings/talha-2--sloplint/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 11 lines
- {
- "name": "sloplint",
- "owner": { "name": "Talha-2" },
- "plugins": [
- {
- "name": "sloplint",
- "source": "./",
- "description": "Rules that keep Claude from shipping AI slop, plus a linter that checks for it."
- }
- ]
- }
README.md · README · 102 lines
- <p align="center">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="assets/logo-dark.svg">
- <img src="assets/logo-light.svg" alt="sloplint" width="360">
- </picture>
- </p>
- <p align="center">
- Catch the problems AI-written code ships with, before they reach review.
- </p>
- <p align="center">
- <a href="https://github.com/Talha-2/sloplint/actions/workflows/ci.yml"><img src="https://github.com/Talha-2/sloplint/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
- <a href="https://www.npmjs.com/package/sloplint-cli"><img src="https://img.shields.io/npm/v/sloplint-cli" alt="npm version"></a>
- <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT license"></a>
- <img src="https://img.shields.io/badge/dependencies-0-brightgreen" alt="zero dependencies">
- </p>
- ---
- sloplint finds the mistakes reviewers keep catching in AI-written code: packages that don't exist, `// ... rest of code` stubs, tests that can't fail, and errors swallowed by empty `catch` blocks.
- It's not an AI detector. Every finding is a real problem, whoever wrote the code.
- ```
- $ npx sloplint-cli --online
- src/server.js
- 2 error "express-schema-guardian" does not exist on npm: likely hallucinated (slopsquatting risk) phantom-import
- 10 warn Error is caught and silently discarded swallowed-error
- 11 error Placeholder instead of real code: "... rest of the handlers" placeholder-code
- tests/server.test.js
- 4 error Assertion compares a constant to itself, so it can never fail hollow-test
- sloplint grade F 3 errors, 1 warning, 0 info (2 files, 18 lines, whole project)
- ```
- This output comes from [`examples/demo`](examples/demo). Run it there to see it yourself.
- ## Get started
- **Check your code.** No install, no config.
- ```bash
- npx sloplint-cli # whole project
- npx sloplint-cli --diff # only what you changed
- ```
- **Teach your coding agent.** Adds the rules for Claude Code, Codex, Cursor, Copilot and other agents, so they check their own work.
- ```bash
- npx sloplint-cli init
- ```
- **Review every pull request.** Adds a GitHub Action that comments on each PR.
- ```bash
- npx sloplint-cli init --ci
- ```
- ## What it catches
- | Rule | Catches |
- |---|---|
- | `phantom-import` | Packages that aren't declared, installed, or real |
- | `placeholder-code` | `// ... rest of code`, `implementation goes here` |
- | `chat-artifact` | `Certainly! Here's the updated code` left in files |
- | `hollow-test` | Tests with no assertions, or `expect(true).toBe(true)` |
- | `swallowed-error` | Empty `catch {}` and `except: pass` with no reason given |
- | `narrating-comment` | Comments that repeat the next line of code |
- | `slop-prose` | Filler like `delve into` and `unlock the full potential` |
- | `emoji-headings` | READMEs with an emoji on every heading |
- Works on JavaScript, TypeScript and Python. The comment and prose rules also cover Go, Rust, Java, C#, Ruby, PHP, Swift, Kotlin and Markdown.
- ## Agent skills
- `npx sloplint-cli init` installs these for Claude Code (`.claude/skills`) and Codex (`.agents/skills`). Each one is a short, plain-language process the agent follows, loaded when the situation comes up rather than only when you ask.
- | Skill | Used when the agent… |
- |---|---|
- | [`sloplint`](skills/sloplint/SKILL.md) | writes or changes code, docs or commits |
- | [`sloplint-review`](skills/sloplint-review/SKILL.md) | reviews a change, including its own work before a commit |
- | [`sloplint-tests`](skills/sloplint-tests/SKILL.md) | writes tests, and proves each one fails when the code is broken |
- | [`sloplint-deps`](skills/sloplint-deps/SKILL.md) | adds a package, after checking it's real, maintained and licensed |
- Agents without skill support (Cursor, Copilot, Gemini CLI) get the core rules through a section in `AGENTS.md`.
- ## Docs
- - [Usage](docs/usage.md): CLI options, GitHub Action, configuration, pre-commit hook
- - [Rules](docs/rules.md): what each rule flags and how to fix it
- - [Writing skills](docs/writing-skills.md): how the agent skills are written, for contributors
- ## Contributing
- Each rule is one file with its own tests, and there's nothing to install. See [CONTRIBUTING.md](CONTRIBUTING.md). False-positive reports are especially welcome.
- ## License
- [MIT](LICENSE)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.