create-visual-readme

create-visual-readme is a skill for Claude Code, Codex from MattModeCode/claude-skills. It costs 162 tokens per session (2,308 once invoked), scanned A, original, MIT.

A guide for creating or updating a project's README.md, the main introduction file shown in a code repository. It focuses on showing visual projects with screenshots or recordings when possible.

In plain words
What is it for?
It helps make visual apps, games, and websites easier to evaluate, and provides a simpler written approach for libraries, command-line tools, and back-end projects.
Why use it?
It helps visitors understand and try a project quickly, especially when a text-only description cannot show how the software looks or works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps make visual apps, games, and websites easier to evaluate, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mattmodecode/claude-skills/create-visual-readme
Install

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.

Any agent
npx skills add MattModeCode/claude-skills --skill create-visual-readme
Clone the repo
git clone --depth 1 https://github.com/MattModeCode/claude-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-visual-readme

README.md
[![agentmods](https://agentmods.dev/badge/skills/mattmodecode/claude-skills/create-visual-readme.svg)](https://agentmods.dev/skills/mattmodecode/claude-skills/create-visual-readme)
Your own site
<a href="https://agentmods.dev/skills/mattmodecode/claude-skills/create-visual-readme"><img src="https://agentmods.dev/badge/skills/mattmodecode/claude-skills/create-visual-readme.svg" alt="Measured on agentmods" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00162 $0.02308
Opus 5 $0.00081 $0.01154
Sonnet 5 $0.00032 $0.00462
Haiku 4.5 $0.00016 $0.00231

Measured 6d ago against content hash d7b1404cf753, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-visual-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 6d 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.

skills/create-visual-readme/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-readme

You're a senior open-source engineer who knows a README's job on a public repo: in ten seconds, make a stranger understand what this is and want to try it. Prose alone rarely does that for a visual project — a moving image and a few real screenshots do. So the default for anything with a runnable UI is: drive the real app, capture it, and lead with those visuals.

Decide the mode first

  • Visual app — a game, desktop GUI, or web app you can launch and see. → Do the full capture-and-showcase flow below. This is the point of this skill.
  • Library / CLI / backend with no visual surface. → Skip capture; jump to Non-visual fallback.

If unsure, check for a main scene / entry window / dev server. When in doubt and it can render something, capture it.


Capture-and-showcase workflow (visual projects)

Worked example throughout: Octet, a Godot rhythm game. Adapt the mechanics to the stack in front of you — the shape of the strategy is what transfers, not the Godot specifics.

1. Assess

  • Find how to launch the real app (not the editor/IDE chrome): the engine binary + project path, or the dev-server URL. Octet: Godot_v4.7.exe --path . opens the game window, no editor toolbar.
  • Confirm ffmpeg is available (needed for the GIF): which ffmpeg (or (Get-Command ffmpeg)).
  • If the project's own instructions mandate design fidelity to mockups, re-fetch the mockups live before you judge whether a screen looks right — don't trust memory.

2. Map the screens + find a clean-capture mode

  • List the handful of screens worth showing: one hero (the core loop in motion) plus 4–6 stills that convey range (e.g. gameplay, content/library browser, editor/creator, community, results/output).
  • Find a way to make each shot look flawless and busy, not empty or mid-fumble:
    • a demo / autoplay / attract mode (Octet has an autoplay mod → perfect run, full combo);
    • or seeded state you set up before capturing (a loaded document, a populated list, a finished result). Trace how the app receives its data (Octet hands charts to gameplay via a PlaySession autoload) and set that up in the harness.

Read the full file on GitHub · 160 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 160 lines · 162 tokens per session scan A d7b1404cf753

Subscribe to this mod's changes

create-visual-readme is a skill published in the GitHub repository MattModeCode/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 162 tokens to every session and 2,308 once invoked, about $0.0008 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.

Related

Other skills, from other repositories