Slop Cop
Slop Cop is an automated prose linter that flags the rhetorical and structural tells of LLM-generated writing — em-dash pivots, hedge stacks, throat-clearing intros, three-item lists, filler intensifiers — and emits a JSON violation report designed for coding agents, not humans. It is explicitly a cliche detector, not an AI detector.
The name crystallized when awnist published the browser-based editor on March 10, 2026 and hit the Hacker News front page on April 17 with 241 points. One day later, yasyf forked it into a Go CLI that installs as a Claude Code / Cursor plugin and auto-revises drafts before the agent returns them.
The yasyf CLI ships 48 rules — 35 instant regex detectors plus 10 Haiku-scored sentence rules and 3 Sonnet document-tier rules — sourced from sneak's LLM_PROSE_TELLS catalog and Wikipedia's Signs of AI Writing. When a coding agent writes prose, the skill runs slop-cop, reads the JSON report, and silently rewrites flagged passages without narrating the edit.
A spell-checker for LLM cliches — it flags the em-dash and the 'not just X, but Y' the way a red squiggle flags 'teh'.
Search Interest
-
Nascent0–7 days
-
Emergent8–30 days
-
Validating ← now31–90 days
-
Rising91–180 days
-
Established180 days +
Why is it emerging now?
awnist's browser linter hit HN front-page on April 17, 2026 with 241 points. Within 48 hours, yasyf forked it into a Go CLI and shipped it as a Claude Code + Cursor plugin that auto-revises agent-written prose — turning a human writing tool into agent guardrails.
Outlook
6-month signal projection and commercial timeline.
Strong dev-signal fork (awnist -> yasyf plugin) but zero search demand and a skeptical HN crowd calling the false-positive rate 'idiocy' on classic prose.
Risk · Garry Tan's Claude skills and jalaalrd's anti-ai-slop-writing skill already occupy the same niche — 'slop cop' as a generic category name may never stick.
Analogs · AI detection · GPTZero · Originality.ai
-
nowOSS plugins, zero revenue
Both forks are MIT. No paid tier, no hosted service, no pricing page exists yet.
-
3-6moTeam-scale agent guardrails
Expect paid Claude Code / Cursor marketplace plugins with custom rule packs for enterprise style guides.
-
6-12moCategory crowds out the name
Garry Tan skills and generic 'anti-slop' writing tools likely absorb the niche before 'slop cop' becomes a standalone brand.
Competition & Opportunity for term “Slop Cop”
Three heuristic signals derived from the tracked queries, the term's monetization cards, and its cluster neighbors. Directional, not audited.
Ideas for term “Slop Cop”
Buildable pitches — turn this term into an article, site, product, post, newsletter, video, or course. Steal any card and run with it.
Wide-open SEO gap. Slop Cop is a cliche linter, not an AI detector, and nobody has written the side-by-side. Feed the same Claude draft to all three and screenshot the diffs.
The /plugin marketplace flow is new enough that nobody has a tutorial. Long-tail queries like 'claude code slop detector' and 'cursor prose linter' are uncontested.
Evergreen glossary pulled from LLM_PROSE_TELLS.md plus screenshots of each rule firing. High backlink value for writing blogs and copywriting newsletters.
Newsrooms, agencies, and technical-writing teams all want house-style linting. Ship a hosted rule-pack store ($19/mo per seat) that plugs into both forks.
tldraw and curl pause PRs over AI-slop. A CI check that runs slop-cop on every PR body and comments the violations is a 200-line wrapper with a clear OSS-maintainer market.
First-person 72-hour window essay. Concrete before-and-after diffs on real PR bodies are the fastest way to ride the April 17 HN wave into LinkedIn and X.
We built agents that write prose. Now we're building agents that read the agent's prose before it reaches us. Slop Cop is the first time that loop closed in a public plugin.
Slop Cop flags em-dashes. Hemingway flags em-dashes. One is a bug, one is a style — and a Go CLI plus 241 Hacker News upvotes can't tell the difference.
What People Search
Long-tail queries from Google Suggest + Trends. Volume and competition are heuristics — directional, not audited. Content Type comes from query shape.
SERP of term “Slop Cop”
What searchers see today — organic results on top, paid ads if anyone's bidding. Ad density is a real-time commercial signal.
FAQ
What is Slop Cop?
Slop Cop is an automated prose linter that flags the rhetorical and structural tells of LLM-generated writing — em-dash pivots, hedge stacks, throat-clearing intros, three-item lists, filler intensifiers — and emits a JSON violation….
Why is Slop Cop emerging now?
awnist's browser linter hit HN front-page on April 17, 2026 with 241 points. Within 48 hours, yasyf forked it into a Go CLI and shipped it as a Claude Code + Cursor plugin that auto-revises agent-written prose — turning a human writing tool into agent guardrails.
When did Slop Cop emerge?
Publicly emerged around 2026-03-10 (about 85 days ago as of 2026-06-03). EarlyTerms first recorded a pipeline signal on 2026-04-19.
Related Terms
Other terms in the same space — aliases, subtypes, competitors, and neighbors to explore next.
- Part of AI Slop AI slop is a pejorative for generative-AI content — text, images, video, pull-requests — that is technically fluent but intellectually… →
- Related Claude Code Claude Code is Anthropic's official command-line coding agent — a terminal tool that reads your codebase, edits files, runs commands,… →
- Related AGENTS.md AGENTS.md is an open, vendor-neutral markdown file placed at the root of a repository that tells AI coding agents (Claude Code, Codex… →
- Related Context Engineering Context engineering is the discipline of curating every token that enters an LLM's context window — system prompt, tools, retrieved… →
- Related AI Agent Identity AI Agent Identity is the emerging set of protocols and file formats that let an autonomous agent prove who it is, what it's authorized… →
- Related Claude Agent SDK Claude Agent SDK is Anthropic's programmatic toolkit for building AI agents on Claude. →
- Also known as
- Competitor ··
- Related
Sources
Primary URLs this report cites — open any to verify the claim yourself.
- 01 yasyf/slop-cop — Claude Code + Cursor plugin github.com ↗
- 02 awnist/slop-cop — original browser editor github.com ↗
- 03 Hacker News — Slop Cop (241 points) news.ycombinator.com ↗
- 04 Show HN — Slop Cop Claude Code / Cursor Plugin news.ycombinator.com ↗
- 05 LLM_PROSE_TELLS.md — sneak's rule taxonomy git.eeqj.de ↗
- 06 Wikipedia — AI slop (parent category) en.wikipedia.org ↗