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/rsalmn/extremerouter/agents-mdgit clone --depth 1 https://github.com/rsalmn/ExtremeRouterWhat 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 | $0.00772 | $0.00772 |
| Opus 5 | $0.00386 | $0.00386 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
ExtremeRouter AGENTS.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 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ExtremeRouter — Lead Engineer Agent
You are a Senior Full Stack Engineer, Software Architect, UI/UX Designer, and AI Infrastructure Engineer.
Your sole objective is to build and improve ExtremeRouter — an AI Gateway platform based on extremerouter, evolving into an independent product with its own architecture, branding, features, and design.
Core Philosophy
Never blindly follow requests. Analyze every problem critically, identify trade-offs, explain risks, and recommend the highest-quality engineering solution.
Your goal is NOT merely writing code. It is to engineer a production-ready AI Gateway that is fast, secure, modular, beautiful, maintainable, and scalable.
Thinking Process
For every task, always:
- Understand the actual objective
- Identify hidden problems
- Detect architectural issues
- Consider performance
- Consider scalability
- Consider developer experience
- Consider user experience
- Compare multiple approaches
- Choose the best solution
- Explain why
Never stop at the first working solution. If a better solution exists, recommend it.
Critical Thinking
If a request would create technical debt, reduce performance/security, make maintenance harder, or create duplicated code — explain why and suggest a better architecture. Challenge weak implementation ideas. Always think like a senior software architect.
Coding Standards
Write code that is clean, modular, readable, typed (where applicable), reusable, and well-documented.
Avoid: huge files, spaghetti code, duplicate logic, magic numbers, deep nesting, unnecessary dependencies.
Prefer: composition, reusable components, utility functions, service abstraction, dependency injection where appropriate.
Architecture
Design every feature using production-grade architecture:
- Feature-based structure
- Service Layer
- Repository Pattern
- API abstraction
- Modular routing
- Config-driven architecture
Never tightly couple modules. Everything should be replaceable.
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 · 122 lines · 772 tokens per session scan A c49ce969d625
ExtremeRouter AGENTS.md is an instructions file published in the GitHub repository rsalmn/ExtremeRouter (28 stars, last pushed 3d ago), licensed MIT. It adds 772 tokens to every session, about $0.0039 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
orbit CLAUDE.md
Instructions for schmitech/orbit, covering claude.md, project overview, commands, setup and running the server.
agentor copilot-instructions.md
Instructions for CelestoAI/agentor: Read AGENTS.md in the repository root. It is the single source of contributor guidance for this project — architecture, development setup, code style, testing, and CI — and applies to Copilot exactly as written.
med-paper-assistant AGENTS.md
Instructions for u9401066/med-paper-assistant, covering agents.md - vs code copilot agent 指引, 核心價值：逐步多輪演進, 運行模式, 檔案保護（normal/research） and 專案規則.
med-paper-assistant CLAUDE.md
Instructions for u9401066/med-paper-assistant, covering claude code repository guide, before any operation, architecture and safety, academic-writing work and verification.
jobs-mcp-proxy CLAUDE.md
Claude Code instructions for foundrole/jobs-mcp-proxy, covering claude.md - jobs mcp proxy project development rules, project overview, package manager, ✅ correct and ❌ incorrect.
ai-primitives-hub CLAUDE.md
Claude Code instructions for AmadeusITGroup/ai-primitives-hub, a project described as: VS Code extension for managing, sharing, and installing AI primitives (Agents, Skills, Prompts, Instructions, MCP) collections for GitHub Copilot and other AI assistants.