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 MattModeCode/claude-skills --skill create-visual-readmegit clone --depth 1 https://github.com/MattModeCode/claude-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/mattmodecode/claude-skills/create-visual-readme)<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>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 | $0.00162 | $0.02308 |
| Opus 5 | $0.00081 | $0.01154 |
| Sonnet 5 | $0.00032 | $0.00462 |
| Haiku 4.5 | $0.00016 | $0.00231 |
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.
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
ffmpegis 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
autoplaymod → 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
PlaySessionautoload) and set that up in the harness.
- a demo / autoplay / attract mode (Octet has an
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.
- 6d ago First seen · 160 lines · 162 tokens per session scan A d7b1404cf753
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.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.