hex1b AGENTS.md

A project guide for coding agents working on Hex1b, a codebase that includes terminal-related components and reusable widgets. It describes the repository layout, technologies, and task-specific instructions.

In plain words
What is it for?
Use it when adding widgets, writing or fixing tests, reviewing APIs, updating documentation, checking documentation accuracy, benchmarking surfaces, or working with .NET Aspire.
Why use it?
It gives an agent the project context and local rules needed to make changes that fit the codebase. It also points to detailed guidance for testing, documentation, performance checks, and other common tasks.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/mitchdenny/hex1b/agents-md
Clone the repo
git clone --depth 1 https://github.com/mitchdenny/hex1b

Made for: Codex, OpenCode.

Per session 3,232 This file is loaded in full into every session.
When invoked 3,232 The same file โ€” it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03232 $0.03232
Opus 5 $0.01616 $0.01616
Sonnet 5 $0.00646 $0.00646
Haiku 4.5 $0.00323 $0.00323

Measured 3d ago against content hash effad8d14326, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hex1b AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 3d 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.

AGENTS.md ยท 299 lines

How it starts

The opening of the file, as written. The whole thing โ€” 299 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Agent Guidelines for Hex1b

This document provides context and conventions for AI coding agents (GitHub Copilot, Claude, Cursor, etc.) working with the Hex1b codebase.

๐Ÿ› ๏ธ Available Skills

This repository includes specialized skills in .github/skills/ that provide detailed guidance for specific tasks. Invoke these skills when working on related tasks - they contain step-by-step procedures, templates, and best practices.

Skill When to Use
widget-creator Creating new widgets (widget records, nodes, theming, tests)
writing-unit-tests Writing unit tests for widgets, nodes, or terminal functionality
test-fixer Diagnosing flaky tests, especially timing-related failures in CI
api-reviewer Reviewing API design, accessibility modifiers, and naming conventions
doc-writer Writing XML API documentation or end-user guides
doc-tester Validating documentation accuracy against library behavior
surface-benchmarker Running performance benchmarks after modifying src/Hex1b/Surfaces/
aspire Working with .NET Aspire (running samples, debugging, MCP tools)

Skills are invoked automatically by AI agents based on the task context. They contain comprehensive procedures that complement the high-level guidance in this file.

๐Ÿ“‹ Project Overview

Hex1b is a .NET library for building terminal user interfaces (TUI) with a React-inspired declarative API. The library ships to NuGet as Hex1b.

Key Technologies

  • .NET 10.0 (preview) - Target framework
  • C# 12+ - Modern C# features enabled
  • MSTest (MSTest.Sdk 4.x with Microsoft.Testing.Platform) - Testing framework
  • .NET Aspire - Used for running sample applications

Repository Layout

src/Hex1b/           โ†’ Main library (THE shipped package)
tests/Hex1b.Tests/   โ†’ Unit tests
samples/             โ†’ Example applications
apphost.cs           โ†’ Aspire app host for samples

๐Ÿ—๏ธ Architecture Concepts

Read the full file on GitHub ยท 299 lines

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. 3d ago First seen ยท 299 lines ยท 3,232 tokens per session scan A effad8d14326

Subscribe to this mod's changes

hex1b AGENTS.md is an instructions file published in the GitHub repository mitchdenny/hex1b (173 stars, last pushed 4d ago), licensed MIT. It adds 3,232 tokens to every session, about $0.0162 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.