# FeedHive AI Slop Detector

> Updated 2026-10-13 · type: tool · category: content-copywriting · status: active · rev 1

FeedHive AI Slop Detector is a free, MIT-licensed 120-pattern 'slop' catalog plus a Claude Code and Codex skill that lints AI writing before it ships.

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing: Free, MIT — git clone or consume patterns.json directly; no signup, payment, or API key for the open artifact.
- Best for: Founders and GTM/content teams running AI-written copy at volume who want a local, inspectable checklist to strip the AI tells before a post ships.
- Not for: Anyone wanting a hosted one-click grader — the hosted web checker at feedhive.com is separate; this is the open pattern file and agent skill you run yourself.
- Last verified: 2026-10-13

- **Canonical:** https://gtmstacker.com/registry/tool/feedhive-ai-slop-detector/
- **Source:** [github · FeedHive/ai-slop-detector](https://github.com/FeedHive/ai-slop-detector) — SimonHoiberg
- **Tags:** content-copywriting, mcp-agents, ai-writing, agent-skills
- **Repository:** https://github.com/FeedHive/ai-slop-detector

## Is FeedHive AI Slop Detector open source?

Yes, FeedHive AI Slop Detector is open source under the MIT license.

## How much does FeedHive AI Slop Detector cost?

Free, MIT — git clone or consume patterns.json directly; no signup, payment, or API key for the open artifact. (free).

## Can I self-host FeedHive AI Slop Detector?

Yes, FeedHive AI Slop Detector can be self-hosted (the source is available under the MIT license).


---

A free, MIT-licensed library of 120 AI-writing "slop" patterns organized into 9 categories, shipped two ways: as a structured `patterns.json` you can wire into any tool, and as an agent skill that drops into Claude Code or Codex so an AI model checks its own draft against the catalog before it publishes. Where most "humanize my AI text" products are hosted black boxes, this one is the raw, inspectable rulebook — clone it, read every pattern, change it, and ship it inside your own stack.

## Provenance

- SPDX license MIT read directly from the repo's LICENSE file via the GitHub license API (`spdx_id: MIT`) — verified, not guessed; the README confirms "use it, change it and ship it in your own tools."
- Authentic repo under the verified FeedHive org (github.com/FeedHive, est. 2020-07-20); sole contributor/creator is SimonHoiberg, the same account as the viral X post and FeedHive's founder — author, org, and post all consistent.
- 120 patterns across 9 categories (matches the claim exactly), 55 stars / 3 forks / 0 open issues, created and last pushed 2026-10-12, not archived — confirmed via GitHub API 2026-10-13.
- Routed around name-squat lookalikes (raj-shroff/ai-slop-patterns with 143 entries, petergyang/no-ai-slop, pavithralamahewa/slop-patterns, and others) — the canonical repo was resolved via the FeedHive org, never by name match.
- Surfaced via the 2026-10-13 OSS X pull; curated from the GTM Stacker signal registry (run 2026-10-13-registry-update-01); license and figures independently verified 2026-10-13.

## Why it matters for a GTM stack

AI now writes a large share of GTM content, and the giveaway tells — the "it's not just X, it's Y" cadence, the rule-of-three everywhere, the em-dash pile-ups — are exactly what makes that content read as machine-made and lose trust. FeedHive, a social-media scheduling company, open-sourced the internal checklist it uses to catch those tells, as both a data file and a drop-in agent skill, under MIT. The honest read: it is a pattern catalog, not a quality engine — it strips obvious tells but will not turn weak writing into good writing, and the "most comprehensive list on the internet" line is the vendor's own framing, not a verified fact. It is also a fresh repo with modest traction. But as a free, local, fully inspectable lint pass for an AI content pipeline, it is a cheap, honest piece of leverage.