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.
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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.
[](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/815-reactflow-diagrams)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/815-reactflow-diagrams"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/815-reactflow-diagrams.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00038 | $0.01113 |
| Opus 5 | $0.00019 | $0.00557 |
| Sonnet 5 | $0.00008 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
815-reactflow-diagrams 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive architecture diagrams (React Flow)
Goal: Ship readable, consistent narrative diagrams in a React SPA using @xyflow/react (React Flow): fixed layout, animated edges where they help, and prose on a sibling page that explains scope (what is in-band vs out-of-band).
This rule complements 800-markdown.mdc (Mermaid in Markdown). Use 800 for static docs diagrams; use 815 when the diagram is TypeScript + React Flow.
When this rule applies
Use for interactive canvases (not image-only figures). Typical stack: React, TypeScript, Vite, Tailwind, optional React Router. Package manager may be Bun or npm per project.
File and route layout (SPA)
Adapt paths to your repo, but keep separation of concerns:
- Diagram:
**/components/diagrams/<Name>Diagram.tsx(or your agreed folder) exporting<Name>Diagram. - Page: route-level view that wraps copy +
<Name />(figure, legend, diagram). - Router and index: register the path and add a card or link from the app home so deep links are discoverable.
- README: document new routes and any
public/reference assets.
React Flow defaults (narrative mode)
- Outer container: bordered, dark background, bounded height (for example
min(88dvh, …)). fitViewwith tunedfitViewOptions(padding,maxZoom) and sensibleminZoom/maxZoomfor the graph size.proOptions={{ hideAttribution: true }}where license allows.- Read-only story:
nodesDraggable={false},nodesConnectable={false}unless the product is an editor. - Canvas chrome:
react-flow darkbase,!bg-slate-950,[&_.react-flow__node]:overflow-visiblewhen handles or labels extend past node boxes. - Dots
Backgroundand Controls styled to match the app (slate theme is common). - Wrap custom node and edge components in
memo(); pass stablenodeTypes/edgeTypesobjects (module scope), not new literals each render. - Prefer
buildNodesAndEdges()returning{ nodes, edges }at module scope for static graphs so types and data stay stable.
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.
- 3d ago First seen · 79 lines · 38 tokens per session scan A a665a644c064
815-reactflow-diagrams is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 7d ago), licensed MIT. It adds 38 tokens to every session and 1,113 once invoked, about $0.0002 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 2026-09-03.
Other cursor rules, from other repositories
nextjs-react-tailwind-cursorrules-prompt-file
Cursor rules for Next.js development with React and Tailwind CSS integration.
react-chakra-ui-cursorrules-prompt-file
Cursor rules for React development with Chakra UI integration.
react-styled-components-cursorrules-prompt-file
Cursor rules for React development with Styled Components integration.
general
Wonder Blocks design system conventions, component patterns, and coding standards.
ant-design
Definitive guidelines for building consistent, performant, and maintainable UIs with Ant Design v6.x, focusing on design tokens, layout, and component usage.
react-chakra-ui---folder-structure
A standard folder layout for React and Chakra UI projects, including separate locations for components, pages, themes, hooks, utilities, and assets. It also defines how Chakra UI theme files are grouped.