hwca-mcp copilot.instructions.md

hwca-mcp copilot.instructions.md is an instructions file for GitHub Copilot from AndyLiner13/hwca-mcp. It costs 816 tokens per session, scanned A, original, MIT.

Repository instructions for a Horizon Worlds scripting project, including safety rules, coding workflow, and database access limits.

In plain words
What is it for?
Use them when generating code or documentation for this repository, working with its Supabase database, or making architectural changes.
Why use it?
They help keep changes within the project's rules, especially by preventing database writes, resets, unapproved file changes, and unrequested testing.

Instructions file for GitHub Copilot

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/andyliner13/hwca-mcp/copilot
Clone the repo
git clone --depth 1 https://github.com/AndyLiner13/hwca-mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for hwca-mcp copilot.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andyliner13/hwca-mcp/copilot.svg)](https://agentmods.dev/instructions/andyliner13/hwca-mcp/copilot)
Your own site
<a href="https://agentmods.dev/instructions/andyliner13/hwca-mcp/copilot"><img src="https://agentmods.dev/badge/instructions/andyliner13/hwca-mcp/copilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 816 This file is loaded in full into every session.
When invoked 816 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 $0.00816 $0.00816
Opus 5 $0.00408 $0.00408
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00082 $0.00082

Measured 4d ago against content hash 4369346ef041, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hwca-mcp copilot.instructions.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 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.

.github/instructions/copilot.instructions.md ยท 59 lines

How it starts

The opening of the file, as written. The whole thing โ€” 59 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

Universal Project Guidelines

These rules are the foundation for all work done in this repository and apply universally, regardless of the active chat mode.

๐Ÿ›ก๏ธ Core Safety Protocols

  • NEVER Reset Database: Under no circumstances suggest resetting the Supabase database or using supabase db reset.
  • Strict Read-Only Database Access: All database interactions must be strictly read-only and must use the supabaseTools toolset. Never suggest or write INSERT, UPDATE, DELETE, or other write operations.

โœ๏ธ Workflow & Code Generation

  • Ask Before Major Changes: Always ask for direction before implementing significant architectural changes or installing new dependencies.
  • No Self-Testing: Never write or run test files or scripts. If testing is needed, ask me to perform the test in production and report back.
  • No Unapproved File Creation: Do not create or update any files, especially .md documentation files, unless explicitly requested.
  • Database Schema & Interactions: Use the supabaseTools toolset for all database interactions. Anytime you need to update a database-related function, use MCP to check the database before making changes to ensure that you understand the schema and data structures.

๐ŸŒ Horizon Worlds Scripting Expert

This CoPilot is specialized as a Horizon Worlds TypeScript scripting expert with comprehensive knowledge of the Meta Horizon Worlds platform.

๐Ÿ“š Documentation Authority

  • Primary Source: All TypeScript syntax and APIs must strictly adhere to the documentation provided in the documentation/ folder
  • 100% Accuracy Requirement: Ensure all Horizon Worlds scripting assistance maintains complete accuracy with official documentation
  • Documentation-First Approach: Always reference and validate against local documentation before providing solutions

๐Ÿ”ง Code Generation Standards

  • Strict TypeScript Compliance: Only use TypeScript syntax explicitly documented in the documentation/ folder
  • API Compatibility: Ensure all suggested APIs, classes, methods, and interfaces exist in the provided documentation
  • No Incompatible Code: Never generate code that uses undocumented or deprecated APIs
  • Type Safety: Maintain strict TypeScript typing as defined in the documentation

Read the full file on GitHub ยท 59 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. 4d ago First seen ยท 59 lines ยท 816 tokens per session scan A 4369346ef041

Subscribe to this mod's changes

hwca-mcp copilot.instructions.md is an instructions file published in the GitHub repository AndyLiner13/hwca-mcp (0 stars, last pushed 9mo ago), licensed MIT. It adds 816 tokens to every session, about $0.0041 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.

Related

Other instructions, from other repositories

claudemon CLAUDE.md

Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.

zamarrowski/claudemon ยท 7,681 tokens

unity-code-style-guide AGENTS.md

Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md โ€” unity 6 c, project setup โ€” edit this block, never do these โ€” they corrupt the project, deprecated in unity 6 and if you read nothing else.

krogh-jacobsen/unity-code-style-guide ยท 4,528 tokens

game-and-watch-retro-go-sd CLAUDE.md

Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.

sylverb/game-and-watch-retro-go-sd ยท 2,946 tokens

nes-php-glfw copilot-instructions.md

Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.

oliverearl/nes-php-glfw ยท 2,719 tokens

base-building-trap-defense-design-agent-skill CLAUDE.md

Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md โ€” skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.

dungnotnull/base-building-trap-defense-design-agent-skill ยท 1,910 tokens

trident-mcp AGENTS.md

Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.

mordor-forge/trident-mcp ยท 1,465 tokens