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 wan-huiyan/cutify-this --skill pop-that-readmegit clone --depth 1 https://github.com/wan-huiyan/cutify-thisWrote 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/wan-huiyan/cutify-this/pop-that-readme)<a href="https://agentmods.dev/skills/wan-huiyan/cutify-this/pop-that-readme"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/pop-that-readme/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/wan-huiyan/cutify-this/pop-that-readme"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/pop-that-readme.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 | $0.00216 | $0.02285 |
| Opus 5 | $0.00108 | $0.01143 |
| Sonnet 5 | $0.00043 | $0.00457 |
| Haiku 4.5 | $0.00022 | $0.00229 |
Grade A, and why
pop-that-readme 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pop That README ✨
Turn a flat, wall-of-text README into a cute, high-signal front page people
actually read and screenshot — the polished house style behind repos like
cutify-this, show-and-tell, and agent-review-panel. One template, a baked-in
hero, and a section recipe. Pop, don't pad.
Problem
A project is good but its README is a grey wall: no hero, no badges, a vague one-liner, a giant prose dump, and the install command buried at the bottom. Visitors bounce in seconds. The fix isn't more words — it's a scannable, characterful front page: a hero that shows the thing, a value prop you grasp in one line, an emoji table you skim, and an install block you can copy without scrolling.
Context / Trigger conditions
Use when any of:
- "Write / generate / redo / polish my README", "make my README pop / cute / pretty".
- "Give my repo a front page / a glow-up", "my README is just a wall of text".
- "Add a hero banner / badges / a feature table / a demo GIF / an install section".
- Open-sourcing a repo and it needs a README that earns a star.
Skip if: a terse internal-only repo (a one-paragraph README is correct), a strict
corporate brand template you must follow, or the doc is an API reference / tutorial /
changelog (different shape — see frontend-design / technical-writing).
The recipe — section order (top to bottom)
A README pops when it's scannable and front-loads value. Use this order; drop sections that don't apply, never reorder the top three.
| # | Section | Why it's there |
|---|---|---|
| 1 | Hero (centered image/ASCII + title + emoji) | First impression; shows the thing in 1 second. Baked-in recipe below. |
| 2 | Badge row | Signals it's alive + legit (license, last-commit, version, "Claude Code skill"). |
| 3 | Value-prop blockquote (one bold sentence) | The single most important line. What it does + for whom, concretely. |
| 4 | Demo image/GIF + <sub> caption |
Show, don't tell. Caption explains what the reader is looking at. |
| 5 | What it does / Why it exists | The concrete problem + the honest payoff (1–2 short paras). |
| 6 | Emoji feature/ingredient table | The proven recipe — skimmable, one emoji + claim + why per row. |
| 7 | Quick start / Install (copy-paste block) | The command, reachable without scrolling far. <details> for variants. |
| 8 | Usage example | A realistic "you say X → it does Y" snippet. |
| 9 | Contributors ("Built with love") | contrib.rocks image when others helped. |
| 10 | Limitations / honesty box | What it's NOT, and where it's weak. Builds trust; separates it from marketing. |
| 11 | License + links | Short footer. |
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.
- 10d ago First seen · 175 lines · 216 tokens per session scan A 7df8969347e8
pop-that-readme is a skill published in the GitHub repository wan-huiyan/cutify-this (1 stars, last pushed 29d ago), licensed MIT. It adds 216 tokens to every session and 2,285 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
bun-sqlite
Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.
cloudflare-email-routing
Cloudflare Email Routing for receiving/sending emails via Workers. Use for email workers, forwarding, allowlists, or encountering Email Trigger errors, worker call failures, SPF issues.
bun-http-server
Use when building HTTP servers with Bun.serve, handling requests/responses, implementing routing, creating REST APIs, or configuring fetch handlers.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.