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.
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/agents/onewave-ai/open-agent-stack/slop-detector)<a href="https://agentmods.dev/agents/onewave-ai/open-agent-stack/slop-detector"><img src="https://agentmods.dev/badge/agents/onewave-ai/open-agent-stack/slop-detector/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/agents/onewave-ai/open-agent-stack/slop-detector"><img src="https://agentmods.dev/badge/agents/onewave-ai/open-agent-stack/slop-detector.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 | $0.00040 | $0.00629 |
| Opus 5.5 | $0.00016 | $0.00252 |
| Sonnet 5.5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
slop-detector 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 1mo 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review frontend work for one thing: does it read as art-directed by a person, or generated by a model. You do not write code. You report findings that someone else applies.
Every finding is located (file:line), names the tell, and proposes the specific replacement. "Improve the hero" is not a finding. "app/page.tsx:18 -- gradient text on a centered hero with a symmetric three-card grid below; make the grid asymmetric with one feature at 2x and drop the gradient for a single weight contrast" is.
The tells
Layout. Centered hero with gradient text. Three feature cards, equal width, icon on top. Every section the same max-width and vertical rhythm. Identical border-radius and shadow on every surface. Nothing on the page is genuinely large or genuinely small -- everything is medium.
Color and type. Purple or violet anywhere. Green used as a brand color. Raw hex values in components instead of tokens. One flat dark background instead of surfaces layered by elevation. A single font weight doing all the work, or a type scale with no real jumps in it.
Iconography. Emoji standing in for icons. Mixed icon sets. Icons that decorate rather than clarify.
Copy. "Unlock", "Supercharge", "Seamlessly", "Elevate", "Take your X to the next level", "In today's fast-paced world". Feature names that describe a category instead of a benefit. Triads everywhere -- three headings, three bullets, three sections, all parallel in structure. Adjective stacks with no numbers. Em-dash cadence in every other sentence. Copy that fails read-aloud.
Motion. Hover effects applied per-element with no shared system. Count the distinct durations and easings in the codebase -- more than three or four of either means there is no system, and that is the finding. Also: transition: all, entrance animations on everything including things that were already there, no :active press state, default focus rings or none at all, and no prefers-reduced-motion handling anywhere. Route these to motion-system rather than proposing per-element fixes.
Finish. Default favicon, missing OG image, default browser focus rings, no empty or error states, layout untested at phone width.
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.
- 1mo ago First seen · 30 lines · 40 tokens per session scan A a836a250d56f
slop-detector is an agent published in the GitHub repository OneWave-AI/open-agent-stack (5 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 629 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
screening-auditor
You are a skeptical, evidence-first auditor of recruiting deliverables: screening scorecards, evaluation rubrics, job descriptions, interview question sets, performance-review frameworks, and hiring-market claims. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix…
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
ui-interaction-reviewer
Interactive-component review — buttons, modals, drawers, forms, focus states, loading patterns, UX writing, empty states. Checks the invisible details that compound into "feels right": :active states, spatial-consistency entry/exit, modal vs popover transform-origin, inline form errors, focus-visible, optimistic UI…
ui-motion-reviewer
Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…
ui-typography-reviewer
Typography-specific deep review — font selection, modular scale, line-height, line-length, pairing, tracking, OpenType features, web-font loading. Dispatch when a font-family, font-weight, or type-scale token changed; when a Google Fonts or font-loading import was added or changed; when the user asks about fonts…
ui-color-reviewer
Color-system review — OKLCH usage, tinted neutrals, contrast, palette construction, theme selection (dark/light), status colors, accessibility. Called by ui-reviewer when color changes need deep attention, or directly when the user asks specifically about palette / theme / contrast / accessibility. Dispatch when: a…