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 uwuclxdy/agenticat --skill maudgit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/maud)<a href="https://agentmods.dev/skills/uwuclxdy/agenticat/maud"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/maud.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.04414 |
| Opus 5 | $0.00009 | $0.02207 |
| Sonnet 5 | $0.00003 | $0.00883 |
| Haiku 4.5 | $0.00002 | $0.00441 |
Grade A, and why
maud 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 8d 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maud (Rust HTML Macro)
Captured 2026-07-10 (maud 0.27.0). To update: re-verify against maud.lambda.xyz + docs.rs/maud, then diff for changes.
Maud is a compile-time HTML macro (html!); markup lives inline in Rust, type-checked at compile time. This skill targets maud 0.27.x (0.27.0, released 2025-02-02).
Maud runs on stable Rust and nightly (better error messages on nightly). Stable-Rust-capable since 0.22.1 (2020-11-02); earlier it needed nightly-only compiler features. MSRV is not documented.
1. Setup
Cargo.toml
[dependencies]
maud = "0.27"
2. Rendering API
html! { ... } returns a Markup value. Markup is a type alias for PreEscaped<String>, a wrapper around an already-escaped HTML string.
| Operation | Result | Notes |
|---|---|---|
html! { ... } |
Markup |
The macro expression's value. |
markup.into_string() |
String |
Consumes the Markup, hands back the built string. |
(DOCTYPE) inside html! |
emits <!DOCTYPE html> |
maud::DOCTYPE is a constant equal to the literal string <!DOCTYPE html>. |
use maud::{html, DOCTYPE};
let page = html! {
(DOCTYPE)
html {
head { title { "My site" } }
body { p { "Hello" } }
}
};
Rendering a Display value: maud::display(x) is a free function that renders any value through its Display impl inside a template. It replaced the old blanket Render for Display impl removed in 0.24.0.
use maud::{html, display};
let n = 42;
html! { p { (display(n)) } };
Note: Markup/PreEscaped has no Display impl (checked against docs.rs 0.27; it implements Render, not Display). Convert to String with .into_string() when you need the raw string. There is no html_to! / write-into-buffer macro (html_debug! was removed in 0.25.0). To write into an existing buffer, use the Render trait's render_to (see §9).
3. Web Framework Integration
Turn on the matching feature flag from the table below and Markup implements the corresponding trait. A handler can then just return Markup directly.
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.
- 8d ago First seen · 502 lines · 17 tokens per session scan A 3ac88e610893
maud is a skill published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 4,414 once invoked, about $0.0001 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
makepad-event-action
A guide to handling mouse, keyboard, touch, and lifecycle events in Makepad. It also explains actions, which let a widget communicate an interaction to its parent.
makepad-widgets
Version: makepad-widgets (dev branch) | Last Updated: 2026-01-19 > > Check for updates: https://crates.io/crates/makepad-widgets.
makepad-dsl
A guide to Makepad’s declarative language for defining interface objects and reusable components. It explains properties, prototypes, inheritance, and the live_design syntax used to compose widgets.
makepad-layout
A guide to arranging Makepad interface elements, including their size, spacing, alignment, and flow. Makepad is a Rust toolkit for building user interfaces.
makepad-skills
Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.
azure-storage-blob-rust
Azure Blob Storage library for Rust. Upload, download, and manage blobs and containers. Triggers: "blob storage rust", "BlobClient rust", "upload blob rust", "download blob rust", "storage container rust", "BlobServiceClient rust".