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 satiricalguru/Agents-skills --skill readme-showcasegit clone --depth 1 https://github.com/satiricalguru/Agents-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/satiricalguru/agents-skills/readme-showcase)<a href="https://agentmods.dev/skills/satiricalguru/agents-skills/readme-showcase"><img src="https://agentmods.dev/badge/skills/satiricalguru/agents-skills/readme-showcase/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/satiricalguru/agents-skills/readme-showcase"><img src="https://agentmods.dev/badge/skills/satiricalguru/agents-skills/readme-showcase.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 | $0.00085 | $0.01612 |
| Opus 5.5 | $0.00034 | $0.00645 |
| Sonnet 5.5 | $0.00017 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
readme-showcase 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 19d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README Showcase
Make a README that sells the project in five seconds and gets someone running it in five minutes. Everything in it must be true for this repo: real screenshots of the real app, commands that actually work and features that actually exist.
Works with any agent that can read files and run shell commands (Claude Code, Codex, Gemini CLI, OpenCode, Cursor and others).
Workflow
1. Understand the project (don't write yet)
- Read the existing README, the package manifest (
package.json,pyproject.toml,Cargo.toml,*.xcodeproj,go.mod), the entry points,.github/workflows,LICENSE, and the existingdocs/andassets/folders. - Find out: what it does, who it's for, what makes it different, the platforms it runs on, how to install and run it, and whether it has a UI, a CLI or is a library.
- Get repo facts with
git remote -vand, ifghis available,gh repo view --json name,description,homepageUrl,licenseInfo,repositoryTopics,stargazerCount. - Keep any content worth saving: license, credits, citations and contributor notes.
2. Capture visuals (the most important step)
Store all media in assets/ (or the existing docs/images/.github/assets). Use lowercase kebab-case names: hero.png, demo.gif, feature-search.png.
| Project type | What to capture | How |
|---|---|---|
| Web app / site | Hero screenshot, 2–4 feature screens, a 5–15 s demo GIF | Start the dev server, then scripts/screenshot.mjs (Playwright) |
| CLI / TUI | A terminal recording of the main command | vhs tape → GIF, or asciinema + agg |
| Desktop / mobile app | Window screenshots, a short screen recording | macOS screencapture -l<winid> / -R x,y,w,h; iOS xcrun simctl io booted screenshot/recordVideo |
| Library / API | A code snippet plus its output; an architecture diagram | Carbon-style code image, or a Mermaid diagram (GitHub renders it) |
| Any | Banner / social preview | scripts/banner.py (SVG, no dependencies) |
Helpers in this skill's scripts/ folder:
screenshot.mjs <url> <out.png> [--width 1440 --height 900 --dark --full]: Playwright screenshot, retina, optionally full page.video-to-gif.sh <in.mp4|mov> <out.gif> [width=900] [fps=15]: high-quality palette GIF through ffmpeg.banner.py --title "Name" --tagline "One line" --out assets/banner.svg [--accent "#7c3aed"]: gradient hero banner that looks good in light and dark themes.demo.tape: a VHS template for CLI demos (vhs scripts/demo.tape).
What ships with it
7 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.
- 19d ago First seen · 75 lines · 85 tokens per session scan A dace70e5a9a4
readme-showcase is a skill published in the GitHub repository satiricalguru/Agents-skills (9 stars, last pushed 10d ago), licensed MIT. It adds 85 tokens to every session and 1,612 once invoked, about $0.0003 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 2026-10-28.
readme-showcase compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| readme-showcasesatiricalguru/Agents-skills | Skill | 9 | 10d ago | MIT | A | 85 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 114k | today | MIT | A | 30 | Claude Code, Codex |
| founder-coachalirezarezvani/claude-skills | Skill | 30k | 4d ago | MIT | A | 41 | Claude Code |
| todosJetBrains/thinkrail | Skill | 8.3k | today | Apache-2.0 | A | 58 | Claude Code, Codex |
| computer-usekirodotdev/KiroCrew | Skill | 4.9k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| meetingskirodotdev/KiroCrew | Skill | 4.9k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| mochi-remindkirodotdev/KiroCrew | Skill | 4.9k | today | Apache-2.0 | A | 20 | Claude Code, Codex |