fullstack-langgraph-nextjs-agent copilot-instructions.md

Repository guidance for a Next.js web application that provides an AI chat agent using LangGraph.js, a framework for agent workflows, and MCP servers, which provide tools to the agent.

In plain words
What is it for?
Use it when changing the agent builder, tool connections, streaming chat endpoint, conversation storage, or related frontend and database code.
Why use it?
It gives the coding agent the project structure, message flow, memory, approval steps, and development commands so it can work consistently in the codebase.

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/agentailor/fullstack-langgraph-nextjs-agent/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/agentailor/fullstack-langgraph-nextjs-agent

Made for: GitHub Copilot.

Per session 1,200 This file is loaded in full into every session.
When invoked 1,200 The same file — 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 $0.01200 $0.01200
Opus 5 $0.00600 $0.00600
Sonnet 5 $0.00240 $0.00240
Haiku 4.5 $0.00120 $0.00120

Measured 2d ago against content hash 05f2d468c471, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fullstack-langgraph-nextjs-agent 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 2d 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/copilot-instructions.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Instructions

This is a Next.js 15 fullstack application that implements an AI agent chat interface using LangGraph.js with Model Context Protocol (MCP) server integration and streaming responses.

Architecture Overview

Core Agent System

  • LangGraph Agent: Built with AgentBuilder class in src/lib/agent/builder.ts - creates a StateGraph with agent→tool_approval→tools flow
  • MCP Integration: Dynamically loads tools from MCP servers stored in Postgres (src/lib/agent/mcp.ts)
  • Persistent Memory: Uses LangGraph's Postgres checkpointer for conversation history across sessions
  • Tool Approval: Implements human-in-the-loop pattern with interrupts for tool execution approval

Data Flow

  1. User message → /api/agent/stream SSE endpoint → streamResponse() in agentService.ts
  2. Agent processes with tools from enabled MCP servers → streams incremental responses
  3. Frontend uses useChatThread() hook with React Query for optimistic UI and streaming
  4. Thread persistence via Prisma → Postgres (threads + MCP server configs)

Essential Development Commands

# Setup (requires Postgres running on port 5434)
docker compose up -d
pnpm install
pnpm prisma:generate
pnpm prisma:migrate

# Development
pnpm dev  # Next.js with Turbopack
pnpm prisma:studio  # Database UI

# Database operations
pnpm prisma:generate  # After schema changes
pnpm prisma:migrate   # Create new migrations

Project-Specific Patterns

Agent Configuration

  • One-time setup: ensureAgent() ensures Postgres checkpointer is initialized before agent creation
  • Dynamic tool loading: MCP servers are queried from database on each agent creation
  • Model flexibility: Supports switching between OpenAI/Google models via AgentConfigOptions

Streaming Architecture

  • SSE with React Query: useChatThread manages optimistic UI + streaming updates
  • Message accumulation: Frontend concatenates text chunks by message ID for smooth UX
  • Tool approval flow: Uses Command objects with resume action instead of regular inputs

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 1,200 tokens per session scan A 05f2d468c471

Subscribe to this mod's changes

fullstack-langgraph-nextjs-agent copilot-instructions.md is an instructions file published in the GitHub repository agentailor/fullstack-langgraph-nextjs-agent (131 stars, last pushed 2mo ago), licensed MIT. It adds 1,200 tokens to every session, about $0.0060 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.