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 instructions/mitchdenny/hex1b/agents-mdgit clone --depth 1 https://github.com/mitchdenny/hex1bWhat 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 | $0.03232 | $0.03232 |
| Opus 5 | $0.01616 | $0.01616 |
| Sonnet 5 | $0.00646 | $0.00646 |
| Haiku 4.5 | $0.00323 | $0.00323 |
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.
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.
๐ ๏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.
๐ 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
๐๏ธ Architecture Concepts
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.
- 3d ago First seen ยท 299 lines ยท 3,232 tokens per session scan A effad8d14326
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.
Other instructions, from other repositories
terminal AGENTS.md
Instructions for browser-use/terminal, covering agent notes, rust rewrite verification loop and terminal ui testing standard.
unifly AGENTS.md
Instructions for hyperb1iss/unifly, covering agents.md, what this repository is, quick command reference, the canonical "before commit" gate and individual gates.
waveloom AGENTS.md
Instructions for Menfre01/waveloom, covering waveloom, ้กน็ฎๆฆ่ฆ, ็ผ็ ่ง่, ไปฃ็ ๅฎกๆฅ and ๅผๅๆต็จ.
lazyazure AGENTS.md
AGENTS.md instructions for matsest/lazyazure, covering lazyazure - agent guidelines, project overview, critical guidelines, 1. tui development with gocui and 2. mutex best practices.
r3bl-open-core AGENTS.md
Instructions for r3bl-org/r3bl-open-core, covering agent instructions for r3bl-open-core, ai agent security & system integrity mandates, 1. critical directory protection, 2. ownership & integrity and 3. execution safety.
microNeo AGENTS.md
Instructions for sollawen/microNeo, covering ๅบๆฌ่งๅ, debug and ๆ ธๅฟๆฆๅฟต.