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 markoblogo/abvx-agent-skills --skill anti-slop-reviewgit clone --depth 1 https://github.com/markoblogo/abvx-agent-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/markoblogo/abvx-agent-skills/anti-slop-review)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/anti-slop-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/anti-slop-review/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/markoblogo/abvx-agent-skills/anti-slop-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/anti-slop-review.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 | $0.00091 | $0.02531 |
| Opus 5 | $0.00046 | $0.01265 |
| Sonnet 5 | $0.00018 | $0.00506 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
anti-slop-review 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Slop Review
Review evidence, not vibes. This skill critiques an implemented interface; it does not replace the brief, design system, accessibility checks, or product requirements.
Use frontend-taste-layer while choosing a visual direction. Use this skill after implementation or on screenshots/live UI. Use design-critique-polish for broader polish and web-quality-audit for full accessibility, performance, privacy, and security coverage.
For prose-only work, use the prose pass below and skip browser-specific checks unless the text is already placed in a live UI.
For prose requests, choose one mode up front:
detect: identify named prose patterns with quoted evidence and bounded fixes; do not rewrite the draft;edit: make the smallest useful rewrite, then run the post-edit eval before returning it.
Authority
Default authority is read and proposal. Inspect files, screenshots, and browser behavior; report findings. Change code only when the user asked to fix or polish the interface. Do not add dependencies, replace a design system, license fonts/assets, or invent brand/customer claims without authorization.
Establish the contract
Before judging style, identify:
- surface and critical user task;
- audience and product/brand register;
- existing tokens, components, and design constraints;
- required breakpoints and input modes;
- references the user explicitly approved.
For dashboards, settings, admin tools, firmware UI, and other utility-first products, clarity and density may correctly outweigh novelty. A familiar pattern is not a defect merely because it is familiar.
Review hierarchy
Classify every finding as exactly one type.
HARD_DEFECT
Observable failures that can block shipment:
- content hidden when JavaScript, hydration, scroll observers, or animation fails;
- clipped text or controls near fixed heights, notches, masks, and
overflow: hidden; - unreadable contrast, missing focus, broken keyboard path, or ignored reduced motion;
- dead controls, fake interactivity, console errors, or missing loading/error/empty states;
- horizontal overflow, broken responsive layout, unsafe tap targets, or misaligned comparison rows;
- content or controls visibly off-center when centering is part of the design.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 206 lines · 91 tokens per session scan A 9db974fade64
anti-slop-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,531 once invoked, about $0.0005 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
screenshot-sweep
Use whenever a screenshot is captured or supplied — a bug report, a Playwright capture, a design review, a "does this look right". Read the WHOLE image, not just the thing it was sent for: sweep it against the defect checklist below, file the findings, and add them to the todo list. When a defect is later reported…
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.