Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lowcountry-AI/guardrail-skillsnpx agentmods add skills/lowcountry-ai/guardrail-skills/slop-scrubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lowcountry-ai/guardrail-skills/slop-scrub)<a href="https://agentmods.dev/skills/lowcountry-ai/guardrail-skills/slop-scrub"><img src="https://agentmods.dev/badge/skills/lowcountry-ai/guardrail-skills/slop-scrub/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lowcountry-ai/guardrail-skills/slop-scrub"><img src="https://agentmods.dev/badge/skills/lowcountry-ai/guardrail-skills/slop-scrub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00117 | $0.02375 |
| Opus 5 | $0.00059 | $0.01188 |
| Sonnet 5 | $0.00023 | $0.00475 |
| Haiku 4.5 | $0.00012 | $0.00237 |
Grade A, and why
slop-scrub scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slop Scrub
You are a ruthless copy editor. Your job is to read text and find every AI writing pattern in it. Then fix them. Then verify the fix didn't introduce new ones.
This skill runs on any text before it leaves the agent. No channel is exempt. No context makes AI-isms acceptable. Even internal notes get scrubbed if they might be forwarded.
Not using Claude Code? This file works as a standalone checklist too — see the README for how to run it as a plain prompt, a git hook, or a CI check with any LLM.
Input
The text to scrub is one of:
- Pasted directly after the
/slop-scrubcommand - The most recent draft the agent just produced (scrub it before showing the user)
- A specific file or message the user references ("scrub the LinkedIn draft I just wrote")
If no text is provided and no draft is in scope, ask the user what to scrub. Don't guess.
The 12-Item Checklist
Run every item. For EACH item, report what you found. "Clean" is acceptable only if you actually checked. Do not skip items. Do not batch them. The whole point is to catch the thing you'd skip.
1. Word scan
Search the text for every word in this banned list. If you find one, list the line it appears in and replace with a plain-English alternative.
Banned words: delve, tapestry, woven, intricate, navigate, navigating, landscape, realm, journey (as metaphor), unleash, unlock, harness, leverage (as verb), elevate, empower, embark, foster, cultivate, illuminate, transcend, paradigm, holistic, robust, seamless, streamline, synergy, ecosystem, cutting-edge, game-changing, revolutionary, transformative, unprecedented, ever-evolving, rapidly evolving, in today's fast-paced world, in the realm of, at the heart of, lies the, the world of, a world where, a testament to, speaks volumes, resonates, meticulous, meticulously, profound, profoundly, nuanced, nuance.
This list is a starting point, not a ceiling. If a word feels like AI reaching for grandeur, flag it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 188 lines · 117 tokens per session scan A c64b6821a701
slop-scrub is a skill published in the GitHub repository Lowcountry-AI/guardrail-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,375 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
concept
This skill should be used when the user asks to "create a concept spec", "retrofit a module", "check spec drift", "run drift detection", "design a new module", "wyx concept", or wants to generate, update, or drift-check CONCEPT.md files. Supports retrofit, greenfield, drift detection, and discovery modes.
map
This skill should be used when the user asks to "generate architecture map", "visualize spec relationships", "create ARCHITECTURE.md", "show concept dependencies", "wyx map", or wants a Mermaid graph with dependency matrix and data flow paths derived from all wyx specs.
audit
This skill should be used when the user asks to "audit spec coverage", "find uncovered modules", "scan for missing specs", "check wyx coverage", "get spec TODO list", "wyx audit", "wyx", or wants a prioritized list of wyx skill commands for uncovered modules. Scans for coverage gaps, pipeline/sync candidates, and…
sync
This skill should be used when the user asks to "document sync patterns", "map sync handlers", "create SYNCS.md", "review sync coordination", "wyx sync", or wants to understand how concepts communicate through orchestrated workflows. Produces SYNCS.md coordination maps.
pipeline
This skill should be used when the user asks to "create a pipeline spec", "document data transformations", "document data flow", "specify pipeline invariants", "wyx pipeline", or wants to design, retrofit, or discover data pipelines with quality invariants and boundary ownership. Produces PIPELINE.md specs.
implement-rule
Implement checks, patterns, and fixtures for an existing rule skeleton.