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 rules/run-llama/flow-maker/llamaindexgit clone --depth 1 https://github.com/run-llama/flow-makerWhat 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 | $0.01041 | $0.01041 |
| Opus 5 | $0.00521 | $0.00521 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
llamaindex 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Understanding @llamaindex/workflow-core (TypeScript)
This document explains the core concepts of the @llamaindex/workflow-core library for TypeScript, which is used by typescript-compiler.ts to generate executable agent scripts. The library uses a functional, event-driven paradigm.
Core Concepts
The workflow is built by defining events and then creating handlers that listen for those events. The execution flow is determined by which events are emitted from handlers.
-
Event-Driven Flow: The entire workflow is orchestrated by events. A handler function executes when it receives an event of a type it's registered to handle. After executing its logic, the handler can emit a new event, which in turn triggers another handler.
-
Functional Approach: Instead of class-based inheritance (like in Python), the TypeScript version uses factory functions to build the workflow.
workflowEvent<T>(): Creates a new type of event.createWorkflow(): Creates a new workflow instance.workflow.handle([...events], handlerFn): Registers a functionhandlerFnto be called when any of the specifiedeventsare detected.
-
Asynchronous by Design: All handlers can be
asyncand are expected to returnPromises, making them suitable for I/O-bound tasks like LLM calls and tool interactions.
Key Components
1. workflowEvent
This function is used to define the different types of events that will flow through your system. They are the data carriers.
import { workflowEvent } from "@llamaindex/workflow-core";
// Define an event that carries a string payload
const startEvent = workflowEvent<string>();
// Define an event that carries a structured object
interface ToolCall {
id: string;
name: string;
args: any;
}
const toolCallEvent = workflowEvent<ToolCall>();
2. createWorkflow and .handle
createWorkflow() creates the main workflow object. The .handle() method is then used to register listeners for specific events. The return value of a handler function becomes a new event that is dispatched into the workflow.
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.
- 2d ago First seen · 95 lines · 1,041 tokens per session scan A c347196a0a2d
llamaindex is a cursor rule published in the GitHub repository run-llama/flow-maker (211 stars, last pushed 8mo ago), licensed MIT. It adds 1,041 tokens to every session, about $0.0052 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 cursor rules, from other repositories
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活:修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.