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 alphacornutum/layercake --skill humanizergit clone --depth 1 https://github.com/alphacornutum/layercakeWrote 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/alphacornutum/layercake/humanizer)<a href="https://agentmods.dev/skills/alphacornutum/layercake/humanizer"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/humanizer/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/alphacornutum/layercake/humanizer"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/humanizer.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 | $0.00200 | $0.02985 |
| Opus 5.5 | $0.00080 | $0.01194 |
| Sonnet 5.5 | $0.00040 | $0.00597 |
| Haiku 4.5 | $0.00020 | $0.00298 |
Grade A, and why
humanizer 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 20d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Rewrite text, or generate prose from scratch, so it reads like a real person wrote it. Clear, direct, grounded. Preserve every fact, claim, and piece of core meaning from the source. Add nothing that is not there. Keep roughly the same length unless the original is bloated.
Two modes
Rewriting existing text. The user pastes something (often AI-written, sometimes their own) and asks for a humanized version. Read the source carefully, then return only the rewritten text in the same language as the input. No preamble, no explanation, no closing remark.
Generating new prose. The user asks for a blog post, essay, article, newsletter, op-ed, short story, or similar deliverable. Apply these same principles from the very first draft so the output never has the AI tells to begin with. Skip the dutiful AI moves while generating: no setup paragraph that explains what you are about to do, no qualifier-laden hedging, no closing summary of what the reader just read.
Apply this style to prose deliverables the user will publish or share. Skip it for code, casual conversational replies, technical documentation, lists the user specifically asked for, or anything where the user explicitly wants a different voice.
Format
Write in flowing paragraphs. If the input has lists, bullets, or bold-header sections, convert them into prose with real transitions. Structure should come from the logic of the ideas, not from visual markup.
Allowed punctuation: commas, periods, parentheses, question marks. Question marks are fine in normal proportion, including the rhetorical kind, because real writers use them constantly. Reserve exclamation marks for a real moment of emphasis or surprise. Filler intensifiers in the AI manner ("This is huge!", "What a game-changer!") are tells — leave them out.
Actively remove the following:
- Em dashes (—), en dashes (–), and hyphens (-) used for pauses or parenthetical asides become commas or separate sentences.
- Colons (:) used for lists or rhetorical framing, the "Feature: explanation" move, become natural sentences.
- Semicolons (;) become periods. The reason this matters: these marks are some of the strongest AI tells in modern text, em dashes especially. Pulling them out forces a sentence-level rewrite that breaks the AI rhythm, which is the whole point.
What ships with it
2 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.
- 20d ago First seen · 146 lines · 200 tokens per session scan A 5b3e90d2a776
humanizer is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 2d ago), licensed MIT. It adds 200 tokens to every session and 2,985 once invoked, about $0.0008 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 2026-09-26.
Other skills, from other repositories
after-effects-scripting
Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
style-guide
Help a motion designer capture their house style — palette, type, motion and layout — into the house-style.md file that sits next to their After Effects project and shapes everything built afterwards. Load when the user asks to create, edit or review their style guide, when they say work does not look like theirs, or…
flue
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
hyperframes-product-launch-video
Create product launch videos from a URL, brief, or script using HyperFrames (HTML→MP4). Use when the user wants a product launch video, site tour, social clip featuring a product's own visuals, or marketing/promoting a product. Up to 3 min (sweet spot 30-90s). Teaches the HyperFrames production loop: plan → write HTML…
hyperframes-motion-graphics
Create short, unnarrated, design-led motion graphics (under 10s) using HyperFrames. Use when the user wants kinetic type, stat/chart hits, logo stings, lower-thirds, animated tweets/headlines, or transparent overlay motion graphics. MP4 or transparent overlay output. Teaches seek-safe keyframe authoring and the 2-3…