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/ehsanghaffar/einbiogpt/copilot-instructionsgit clone --depth 1 https://github.com/ehsanghaffar/einbiogptWhat 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 | $0.01115 | $0.01115 |
| Opus 5 | $0.00558 | $0.00558 |
| Sonnet 5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
einbiogpt copilot-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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BioGPT Copilot Instructions
AI-powered social media bio generator built with Next.js, TypeScript, and OpenAI.
Project Architecture
Full-stack web app with client-side UI and server-side LLM generation:
- Frontend: React 18 client components in app/page.tsx with form inputs (text, platform, tone)
- Backend: Next.js API routes calling OpenAI/LangChain
- Integration: LangChain
LLMChainwithChatOpenAI(gpt-4o)for bio generation via app/api/generate/route.ts - Direction: Persian/Farsi with RTL (
dir="rtl"on html element in app/layout.tsx)
Data flow: Form input → /api/generate POST → ChatOpenAI LLMChain PromptTemplate → Generated bio text
Rate Limiting & Error Handling
IP-based rate limiting with Redis support (production) or in-memory fallback (development):
- Unified implementation: lib/rate-limit.ts
- RateLimitError class defined in lib/rate-limit.ts
- Configurable via env vars:
REDIS_URL,RATE_LIMIT_WINDOW,RATE_LIMIT_MAX - Client-side cooldown:
NEXT_PUBLIC_COOLDOWN_TIMEenv var (default 10s) - managed in page.tsx state - API returns JSON errors with Persian messages:
{ error: "لطفاً تمام فیلدهای مورد نیاز را پر کنید." }
Key Patterns & Conventions
Environment Variables
NEXT_OPENAI_API_KEY: OpenAI API key (server-side only, NOT prefixed with NEXT_PUBLIC_)NEXT_PUBLIC_COOLDOWN_TIME: Cooldown in seconds between requestsREDIS_URL: Redis connection URL for production rate limiting (optional)RATE_LIMIT_WINDOW: Rate limit window in milliseconds (default: 60000)RATE_LIMIT_MAX: Max requests per window per IP (default: 10)
Styling & UI
- Tailwind CSS with RTL support; HSL CSS variables in styles/globals.css
- shadcn/ui components: components/ui/* (button, card, textarea, tabs, select, badge)
- Animations: Framer Motion (
MotionCard,MotionButton) - Notifications: Sonner toast (
sonner) for success/error messages
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 · 83 lines · 1,115 tokens per session scan A 9e62ef89720e
einbiogpt copilot-instructions.md is an instructions file published in the GitHub repository ehsanghaffar/einbiogpt (19 stars, last pushed 7d ago), licensed MIT. It adds 1,115 tokens to every session, about $0.0056 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
generative-ai-for-beginners AGENTS.md
Instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.
LightRAG AGENTS.md
AGENTS.md instructions for HKUDS/LightRAG, covering repository guidelines, project overview, project structure, module layout (lightrag/) and core architecture.
helicone CLAUDE.md
Instructions for Helicone/helicone, covering claude.md, project overview, core architecture, services and data flow.
langroid CLAUDE.md
Instructions for langroid/langroid, covering claude.md, commands, development, testing and linting and type checking.
helicone AGENTS.md
Instructions for Helicone/helicone, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
AstrBot AGENTS.md
AGENTS.md instructions for AstrBotDevs/AstrBot, covering setup commands, core, dashboard(webui), pre-commit setup and dev environment tips.