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 aixarizzo/kill-slop --skill anti-slopgit clone --depth 1 https://github.com/aixarizzo/kill-slopWrote 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/aixarizzo/kill-slop/anti-slop)<a href="https://agentmods.dev/skills/aixarizzo/kill-slop/anti-slop"><img src="https://agentmods.dev/badge/skills/aixarizzo/kill-slop/anti-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/aixarizzo/kill-slop/anti-slop"><img src="https://agentmods.dev/badge/skills/aixarizzo/kill-slop/anti-slop.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 | $0.00138 | $0.02534 |
| Opus 5 | $0.00069 | $0.01267 |
| Sonnet 5 | $0.00028 | $0.00507 |
| Haiku 4.5 | $0.00014 | $0.00253 |
Grade A, and why
anti-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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anti-slop
Slop is not a vocabulary problem. It is manufactured upstream: alignment training collapses output toward the statistical mean (mode collapse, driven by typicality bias in preference data — arXiv 2510.01171), single-sample generation returns the most typical completion, and a context starved of specifics can only produce the average of everything. Banned-word lists treat the symptom. At adoption scale they mint a new house style — the zero-em-dash, no-adverbs voice is already its own tell, and Wikipedia's own tells-catalog maintainers warn that scrubbing signs "could just make detection harder."
The job: make the output sound like a specific person with something specific to say. Both halves are mandatory. This skill intervenes at four layers and measures whether it worked. It is a writing-quality protocol, not a detector-evasion tool.
Modes
| Mode | When | Run |
|---|---|---|
| DRAFT | writing new text | Layers 1→2→3→4, ship with score |
| AUDIT | handed existing text | Layers 3→4, report score before/after + fix list |
The contract — verify before generating anything
Two inputs separate writing from slop. Check both first:
1. A bound voice. In priority order:
- an explicit voice spec (voice file, brand guide), or
- 5+ writing samples from the author → build a voice card on the fly (
references/voice-binding.md), or - a named register the user states ("tired senior engineer in Slack", "group-chat shitposter who knows finance").
If none exists: STOP and say so. Offer the choice: "Give me 5+ samples or name a register — otherwise I can deliver clean-generic, which reads fine but sounds like no one." NEVER silently fall back to a default voice. A default voice shipped by every agent is the next generation of slop.
2. Specifics. At least 3 concrete particulars the text can stand on: a number, a name, a date, a moment, a place, a mechanism, a contradiction, a thing that broke. No specifics in context → get them (ask the user, or pull from the material available to you). Never invent particulars to fill the gap. If neither is possible, say: "No specifics available — anything I write will be generic by construction." That sentence is more useful than the slop would have been.
What ships with it
5 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.
- 10d ago First seen · 138 lines · 138 tokens per session scan A 9fce662eec53
anti-slop is a skill published in the GitHub repository aixarizzo/kill-slop (18 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 2,534 once invoked, about $0.0007 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
humanize-pro
Use when the user asks to humanize, unslop, de-slop, de-AI, clean up, tighten, or make text sound human or natural; when they say something reads like AI or like ChatGPT; when they ask whether something matches their voice or style guide; or when drafting or rewriting outbound human communication: LinkedIn posts and…
anti-ai-writing
Use when writing or editing any prose for a human reader - documentation, READMEs, emails, reports, captions, scripts, blog posts, UI copy, commit messages, PR descriptions - or when asked to remove AI tells, de-slop text, make writing sound human, or check writing style. Applies 29 researched patterns that make text…
humanizer
Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic…
authenticity-check
Score how authentically text reads as a real human author's work, flag spans that read as AI-generated, AI-templated, or generically derivative, and run a separate read-only scan for suspicious Unicode provenance carriers. Return an authenticity band, a 0-100 score, provenance signals, and span-level reasons. Use when…
ai-slop-detector
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
humanizer-czech
Odstraň znaky AI-generovaného psaní z českého textu. Použij při editaci nebo revizi textu, aby zněl přirozeněji a lidštěji. Detekuje a opravuje 27 vzorců včetně: nafouklého významu, propagačního jazyka, anglického slovosledu, kalků, nominalizace, monotónního rytmu, nadužívání spojek, typických českých AI klišé…