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/raffertyuy/github-copilot-prompts/tsgit clone --depth 1 https://github.com/raffertyuy/github-copilot-promptsWhat 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 | $0.00289 | $0.00289 |
| Opus 5 | $0.00144 | $0.00144 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
github-copilot-prompts ts.instructions.md 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 yesterday.
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.
What it actually says
TypeScript Coding Best Practices
TypeScript-Specific Guidelines
- Prefer
constandletovervarfor variable declarations. - Use type annotations for function parameters, return types, and variables.
- Prefer interfaces over type aliases for object shapes.
- Avoid using
any; use specific types or generics where possible. - Use ES6+ features and syntax.
Formatting
- Use semicolons consistently.
- Use single quotes for strings, except when escaping is easier with double quotes.
Error Handling
- Use try/catch blocks for asynchronous code and handle errors gracefully.
- Avoid using bare
catchclauses; specify the error type if possible.
Documentation
- Add JSDoc comments to all public classes, interfaces, functions, and methods.
Testing
- Write unit tests for all functions and classes.
- Use frameworks like Jest or Mocha.
- Name test files and functions clearly.
File and Directory Structure
- Use lowercase with hyphens for file and folder names.
- Organize code into modules and folders logically.
- Place executable code inside
mainor entry-point files.
Performance
- Profile and optimize only after identifying bottlenecks.
- Use built-in data structures and libraries where possible.
Version Control
- Commit code with clear, concise messages.
- Do not commit secrets or large binary files.
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.
- yesterday First seen · 40 lines · 289 tokens per session scan A 01979de291c7
github-copilot-prompts ts.instructions.md is an instructions file published in the GitHub repository raffertyuy/github-copilot-prompts (43 stars, last pushed 5mo ago), licensed MIT. It adds 289 tokens to every session, about $0.0014 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.
Other instructions, from other repositories
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
react-seed AGENTS.md
Instructions for guokaigdg/react-seed, covering agents.md, 目录, 1. 项目概览, 2. 技术栈 and 3. 目录结构.
actual-mcp AGENTS.md
Instructions for s-stefanov/actual-mcp, covering 🔄 project awareness & context, 🧱 code structure & modularity, 🧪 testing & reliability, 📎 style & conventions and 📚 documentation & explainability.
moss AGENTS.md
Instructions for D-Robotics/moss, covering agents.md, 仓库身份, 文档所有权与阅读顺序, 代码规范执行摘要(必须遵守) and 第一次进入仓库.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
svelte-markdown CLAUDE.md
Instructions for humanspeak/svelte-markdown, covering claude.md, project overview, key technologies, project structure and development commands.