base

A set of project rules describing the technologies and implementation details of a Llama Agent Creator application.

In plain words
What is it for?
Use it when building or changing the Next.js and TypeScript interface, visual workflow editor, generated workflows, language-model integrations, or Vitest tests.
Why use it?
It gives contributors a shared reference for the app’s framework, workflow engine, model connections, data storage, and testing setup.

Cursor rule for Cursor

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 rules/run-llama/flow-maker/base
Clone the repo
git clone --depth 1 https://github.com/run-llama/flow-maker

Made for: Cursor.

Per session 602 This file is loaded in full into every session.
When invoked 602 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 $0.00602 $0.00602
Opus 5 $0.00301 $0.00301
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured yesterday against content hash 8848c913fed4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

base 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.

.cursor/rules/base.mdc · 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.

Llama Agent Creator: Technical Details Supplement

This document supplements the main architecture.mdc file by providing specific details about the technologies and implementation of the Llama Agent Creator.

Application Stack

  • Framework: Next.js
  • Language: TypeScript
  • UI Library: React with shadcn/ui components.
  • Graph Visualization: @xyflow/react is used to build the interactive workflow editor in AgentFlow.tsx.
  • State & Storage:
    • The visual graph's state (nodes and edges) is persisted to localStorage.
    • Global chat state is managed via React Context in src/components/ChatProvider.tsx.
  • Core Workflow Engine: @llamaindex/workflow-core provides the foundational classes and logic for creating and running workflows in the generated TypeScript code.
  • LLM Integrations: The application uses @llamaindex/openai, @llamaindex/anthropic, and @llamaindex/google to connect to various language models.
  • Testing: The project is set up with Vitest for testing.

File-Specific Details

This section clarifies the roles of key files and directories not fully detailed in the high-level architecture diagram.

  • app/api/: This directory contains the backend serverless functions that the interactive runner (RunView.tsx) calls. For instance, when a promptLLM node is executed in the UI, it makes a POST request to app/api/llm/call/route.ts to get the model's response.

  • src/components/nodes/: This directory contains the React components for each type of node that can be dragged onto the canvas (e.g., PromptLLMNode.tsx, DecisionNode.tsx, UserInputNode.tsx). These components define the appearance and configuration options of each node in the editor.

  • src/components/CompileView.tsx: This component provides the user interface for triggering the TypeScript compilation and viewing/downloading the generated code.

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.

  1. yesterday First seen · 39 lines · 602 tokens per session scan A 8848c913fed4

Subscribe to this mod's changes

base is a cursor rule published in the GitHub repository run-llama/flow-maker (211 stars, last pushed 8mo ago), licensed MIT. It adds 602 tokens to every session, about $0.0030 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.