Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tushaarmehtaa/tushar-skills --skill remove-ai-slopgit clone --depth 1 https://github.com/tushaarmehtaa/tushar-skillsWrote 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/tushaarmehtaa/tushar-skills/remove-ai-slop)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/remove-ai-slop"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/remove-ai-slop/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/tushaarmehtaa/tushar-skills/remove-ai-slop"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/remove-ai-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.06043 |
| Opus 5 | $0.00016 | $0.03021 |
| Sonnet 5 | $0.00006 | $0.01209 |
| Haiku 4.5 | $0.00003 | $0.00604 |
Grade A, and why
remove-ai-slop 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 — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the actual interface, not just a list of fashionable motifs. Remove unmistakable defaults forcefully. Judge softer patterns by whether they fit the product, content, and brand or merely repeat a learned template.
Never turn the cleanup into another house style. Do not make every interface flat, dark, minimally rounded, or monochrome by default.
Use three verdicts
HARD BAN
Use this only for exact unfinished-copy, semantic-duplication, consequential-ambiguity, fabricated-evidence, or similarly objective definitions below. One confirmed occurrence is enough. Visual taste, common components, geometry, fonts, and decorative motifs do not qualify by themselves.
Use this verdict:
HARD BAN — [pattern]. [Why it fails]. Remove it. [Repair direction].
Allow only the narrow semantic exceptions listed with that pattern. “It is a brand choice” is not evidence by itself.
STRONG PRESUMPTION
Use this for patterns that can work but usually read as defaults when unsupported or repeated. Require a concrete product, content, functional, or documented brand reason to keep one.
Use this verdict:
STRONG PRESUMPTION — [pattern] reads as a reused default because [evidence]. Keep it only if [specific purpose]; otherwise [repair].
CONTEXTUAL SIGNAL
Use this for neutral design or copy vocabulary that becomes slop only through repetition, mismatch, co-occurrence, or dominance. Do not report an isolated low-confidence motif as a defect.
Keep accessibility, semantics, performance, and factual-integrity defects in a separate QUALITY DEFECTS section. They matter, but they are not proof of AI authorship.
Phase 1: Establish context
Choose an audit scope before inventorying the repository:
- Focused — one route, component family, flow, or reported pattern. Inspect every meaningful state inside that boundary.
- Representative — the default for a product-wide review. Sample each distinct page role, shared chrome, major component system, and high-risk flow; include enough routes to test convergence without rendering every sibling page.
- Exhaustive — every in-scope route, locale, channel, and meaningful state. Use when the user explicitly requests full coverage or when regulated, release-blocking, or migration work justifies the cost.
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 · 465 lines · 32 tokens per session scan A 1cb2c72dc171
remove-ai-slop is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 6,043 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.