template rules.instructions.md

Instructions for snowdreamtech/template, covering ๐Ÿšจ critical system instruction ๐Ÿšจ, step 1: read all core rule files, step 2: read relevant language & framework rule files and why this file exists.

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/snowdreamtech/template/rules
Clone the repo
git clone --depth 1 https://github.com/snowdreamtech/template

Made for: GitHub Copilot.

Per session 543 This file is loaded in full into every session.
When invoked 543 The same file โ€” it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00543 $0.00543
Opus 5 $0.00271 $0.00271
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured today against content hash 45f7f745953f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

template rules.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 today.

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/rules.instructions.md ยท 40 lines

How it starts

The opening of the file, as written. The whole thing โ€” 40 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

๐Ÿšจ CRITICAL SYSTEM INSTRUCTION ๐Ÿšจ

Before answering ANY prompt or executing ANY code in this repository, you MUST first read and strictly adhere to ALL the rules defined in the following directory:

Step 1: Read ALL Core Rule Files

๐Ÿ“ .agent/rules/ โ€” Read in numerical order:

  1. .agent/rules/01-general.md โ€” Language, communication, idempotency, cross-platform, network, security & audit
  2. .agent/rules/02-coding-style.md โ€” Commit messages, code quality, error handling, documentation, naming conventions
  3. .agent/rules/03-architecture.md โ€” Project structure, AI IDE integration, design principles
  4. .agent/rules/04-security.md โ€” Credentials, access control, encryption, scanning, incident response
  5. .agent/rules/05-dependencies.md โ€” Locking, integrity, auditing, release process, changelog
  6. .agent/rules/06-ci-testing.md โ€” Test types, CI pipeline, test data, fast feedback, quality gates
  7. .agent/rules/07-git.md โ€” Commits, branching, pull requests, code review, history hygiene
  8. .agent/rules/08-dev-env.md โ€” Environment consistency, dev container, scripts, pre-commit hooks, debugging
  9. .agent/rules/09-ai-interaction.md โ€” Safety boundaries, code generation, communication, context handling, quality
  10. .agent/rules/10-ui-ux.md โ€” Styling, componentization, accessibility, performance, i18n (frontend projects only)
  11. .agent/rules/11-deployment.md โ€” Containerization, secrets, deployment pipeline, IaC, observability & DR

Step 2: Read Relevant Language & Framework Rule Files

After reading the core rules, inspect the project's file structure and configuration files to identify the languages and frameworks in use. Then read the corresponding rule files from .agent/rules/.

Why This File Exists

This project uses a unified rule system to ensure consistent AI behavior across all AI-powered IDEs and tools (Cursor, Windsurf, GitHub Copilot, Cline, Claude, Gemini, Trae, Roo Code, Augment, Amazon Q, Kiro, Continue, Junie, etc.). This file is a redirect entry point โ€” the actual rules live in .agent/rules/ as the Single Source of Truth.

Read the full file on GitHub ยท 40 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. today First seen ยท 40 lines ยท 543 tokens per session scan A 45f7f745953f

Subscribe to this mod's changes

template rules.instructions.md is an instructions file published in the GitHub repository snowdreamtech/template (15 stars, last pushed yesterday), licensed MIT. It adds 543 tokens to every session, about $0.0027 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 2026-09-01.

Related

Other instructions, from other repositories