What is AI-System-Design-Consultant CLAUDE.md?

Project instructions for an automated system-design interview application. The application uses FastAPI and LangGraph to route design questions through specialist AI agents, with a local Ollama model producing typed design results.

Use them when modifying the design workflow, API endpoints, specialist agents, local model setup, or project structure.

They explain how to run the system and highlight constraints such as its required local model, unusual file paths, and in-memory-only session recovery.

How deepanshu2711/AI-System-Design-Consultant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to deepanshu2711/AI-System-Design-Consultant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/deepanshu2711/AI-System-Design-Consultant/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/deepanshu2711/AI-System-Design-Consultant

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/deepanshu2711/ai-system-design-consultant/claude-md/github.svg)](https://agentmods.dev/instructions/deepanshu2711/ai-system-design-consultant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/deepanshu2711/ai-system-design-consultant/claude-md"><img src="https://agentmods.dev/badge/instructions/deepanshu2711/ai-system-design-consultant/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/deepanshu2711/ai-system-design-consultant/claude-md"><img src="https://agentmods.dev/badge/instructions/deepanshu2711/ai-system-design-consultant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 674 This file is loaded in full into every session.

When invoked 674 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00674	$0.00674
Opus 5.5	$0.00270	$0.00270
Sonnet 5.5	$0.00135	$0.00135
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash d33b70af4b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AI-System-Design-Consultant CLAUDE.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 2mo 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.

CLAUDE.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A FastAPI + LangGraph multi-agent system that conducts an automated system-design "interview": a supervisor node routes a shared DesignState through specialist LLM agents (clarifying questions, requirement analysis, traffic estimation, capacity planning, database/cache/queue/CDN/storage/API design), each emitting a Pydantic-typed design artifact. All agents share one local Ollama model via langchain-ollama.

Running it

uv run fastapi dev app/main.py

Requires a local Ollama daemon running with qwen2.5:3b pulled — the model is hardcoded in app/utils/llm_factory.py (no env var override). There is no Docker setup; Ollama must be installed and running on the dev machine.

Endpoints: POST /design/start kicks off a new graph run; POST /design/resume resumes an interrupted run (human-in-the-loop clarification) via LangGraph's Command(resume=...). Checkpointing is in-memory (MemorySaver) only — state does not survive a process restart.

Load-bearing typos — do not "fix" these paths

app/grpahs/supervisor_graph.py (not graphs)
app/state/desgin_state.py (not design_state)

These misspellings are intentional-for-now and other code imports from these exact paths. Renaming them will break imports across the codebase.

Agent node pattern

Every file in app/agents/ follows the same shape: build messages → bind tools → tool-call loop capped by MAX_TOOL_ITERATIONS → force final structured output → return Command(goto="supervisor", update={...}). The supervisor (app/agents/supervisor.py) is the sole router; agents never call each other directly. System prompts live in app/prompts/<agent_name>/v1.py (versioned per agent — bump to v2.py etc. rather than editing v1 in place if iterating on a prompt). Tools shared across agents live in app/tools/ (calculator.py, json_formatter.py).

Current WIP state

Read the full file on GitHub · 39 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.

2mo ago First seen · 39 lines · 674 tokens per session scan A d33b70af4b02

Subscribe to this mod's changes

AI-System-Design-Consultant CLAUDE.md is an instructions file published in the GitHub repository deepanshu2711/AI-System-Design-Consultant (2 stars, last pushed 1mo ago), licensed MIT. It adds 674 tokens to every session, about $0.0027 per session on Opus 5.5. 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 2026-08-31.

LangChain Multi-Agent agents fastapi langgraph langsmith

AI-System-Design-Consultant CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AI-System-Design-Consultant CLAUDE.mddeepanshu2711/AI-System-Design-Consultant	Instructions file	2	1mo ago	MIT	A	674	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AI-System-Design-Consultant: Instructions file for Claude Code