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 agentmods add skills/mitchdenny/hex1b/widget-creatornpx skills add mitchdenny/hex1b --skill widget-creatorgit clone --depth 1 https://github.com/mitchdenny/hex1bWrote 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/mitchdenny/hex1b/widget-creator)<a href="https://agentmods.dev/skills/mitchdenny/hex1b/widget-creator"><img src="https://agentmods.dev/badge/skills/mitchdenny/hex1b/widget-creator.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 | $0.00046 | $0.07131 |
| Opus 5 | $0.00023 | $0.03565 |
| Sonnet 5 | $0.00009 | $0.01426 |
| Haiku 4.5 | $0.00005 | $0.00713 |
Grade A, and why
widget-creator 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 4d 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 — 958 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Widget Creator Skill
This skill provides a comprehensive step-by-step guide for AI coding agents to create new widgets in the Hex1b TUI library. Widgets are the building blocks of Hex1b applications, following a declarative pattern inspired by React.
Overview
Creating a widget in Hex1b involves several coordinated files:
| File | Purpose |
|---|---|
src/Hex1b/Widgets/{Name}Widget.cs |
Immutable widget record (describes what to render) |
src/Hex1b/Nodes/{Name}Node.cs |
Mutable node class (manages state, renders) |
src/Hex1b/{Name}Extensions.cs |
Fluent API extension methods |
src/Hex1b/Theming/{Name}Theme.cs |
Theme elements (colors, characters) |
tests/Hex1b.Tests/{Name}NodeTests.cs |
Unit tests |
Step-by-Step Process
Step 1: Define the Widget Record
Widgets are immutable record types that describe the desired UI. They capture configuration and event handlers but contain no rendering logic.
Location: src/Hex1b/Widgets/{Name}Widget.cs
Key principles:
- Use primary constructor parameters for required data
- Use
internalproperties withinitfor optional configuration - Event handlers use
Func<TEventArgs, Task>?pattern - Provide sync and async overloads for event handlers using
this with { }pattern - Implement
Reconcile()to create/update the corresponding node - Implement
GetExpectedNodeType()to return the node type
Template:
using Hex1b.Events;
using Hex1b.Nodes;
namespace Hex1b.Widgets;
/// <summary>
/// Brief description of what the widget does.
/// </summary>
/// <param name="PrimaryProperty">Description of the main property.</param>
public sealed record MyWidget(string PrimaryProperty) : Hex1bWidget
{
/// <summary>
/// ActionId for the activate action. Use "WidgetName.ActionName" naming
/// convention (PascalCase, omit "Widget" suffix from the widget name).
/// Define one static readonly ActionId per rebindable action.
/// </summary>
public static readonly ActionId Activate = new($"{nameof(MyWidget)}.{nameof(Activate)}");
/// <summary>
/// Optional configuration property.
/// </summary>
internal bool SomeOption { get; init; }
/// <summary>
/// Event handler for some action.
/// </summary>
internal Func<MyEventArgs, Task>? ActionHandler { get; init; }
/// <summary>
/// Sets a synchronous action handler.
/// </summary>
public MyWidget OnAction(Action<MyEventArgs> handler)
=> this with { ActionHandler = args => { handler(args); return Task.CompletedTask; } };
/// <summary>
/// Sets an asynchronous action handler.
/// </summary>
public MyWidget OnAction(Func<MyEventArgs, Task> handler)
=> this with { ActionHandler = handler };
internal override Hex1bNode Reconcile(Hex1bNode? existingNode, ReconcileContext context)
{
var node = existingNode as MyNode ?? new MyNode();
// Mark dirty if properties changed
if (node.PrimaryProperty != PrimaryProperty || node.SomeOption != SomeOption)
{
node.MarkDirty();
}
node.PrimaryProperty = PrimaryProperty;
node.SomeOption = SomeOption;
node.SourceWidget = this;
// Convert typed event handler to internal handler if needed
if (ActionHandler != null)
{
node.ActionCallback = async ctx =>
{
var args = new MyEventArgs(this, node, ctx);
await ActionHandler(args);
};
}
else
{
node.ActionCallback = null;
}
return node;
}
internal override Type GetExpectedNodeType() => typeof(MyNode);
}
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.
- 4d ago First seen · 958 lines · 46 tokens per session scan A 067b740e0368
widget-creator is a skill published in the GitHub repository mitchdenny/hex1b (173 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 7,131 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
write-documentation
Write and format Rust documentation correctly. Apply proactively when writing code with rustdoc comments (//! or ///). Covers voice & tone, prose style (opening lines, explicit subjects, verb tense), structure (inverted pyramid), intra-doc links (crate:: paths, reference-style), constant conventions (binary/byte…
organize-modules
Apply private modules with public re-exports (barrel export) pattern for clean API design. Includes conditional visibility for docs and tests. Use when creating modules, organizing mod.rs files, or before creating commits.
check-bounds-safety
Apply type-safe bounds checking patterns using VPIndex/VPLength types instead of usize. Use when working with arrays, buffers, cursors, viewports, or any code that handles indices and lengths.
check-code-quality
Run comprehensive Rust code quality checks including compilation, linting, documentation, and tests. Use after completing code changes and before creating commits.
analyze-performance
Establish performance baselines and detect regressions using flamegraph analysis. Use when optimizing performance-critical code, investigating performance issues, or before creating commits with performance-sensitive changes.
run-clippy
Run clippy linting, enforce comment punctuation rules, format code with cargo fmt, and verify module organization patterns. Use after code changes and before creating commits.