react-flow-advanced

react-flow-advanced is a skill for Claude Code from existential-birds/beagle. It costs 42 tokens per session (3,248 once invoked), scanned A, original, Apache-2.0.

A guide to advanced React Flow patterns for complex node-and-link interfaces. It covers grouped sub-flows, custom connection lines, drag-and-drop, undo and redo, automatic positioning, and synchronized state.

In plain words
What is it for?
Use it to implement grouped nodes, dropping new nodes onto a canvas, custom connection feedback, undo and redo, automatic layouts, and related advanced behavior.
Why use it?
It helps avoid subtle interaction and coordinate mistakes in editors that go beyond a basic diagram.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the beagle-react plugin — 27 skills shipped together

Good fit Use it to implement grouped nodes, dropping new nodes onto a canvas, custom connection feedback, undo and redo, automatic layouts, and related advanced behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/existential-birds/beagle/react-flow-advanced
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.

Any agent
npx skills add existential-birds/beagle --skill react-flow-advanced
Clone the repo
git clone --depth 1 https://github.com/existential-birds/beagle

Made for: Claude Code.

Or install beagle-react, the plugin that ships this one along with the rest of its 27 skills.

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.

agentmods badge for react-flow-advanced

README.md
[![agentmods](https://agentmods.dev/badge/skills/existential-birds/beagle/react-flow-advanced/github.svg)](https://agentmods.dev/skills/existential-birds/beagle/react-flow-advanced)
Your own site
<a href="https://agentmods.dev/skills/existential-birds/beagle/react-flow-advanced"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/react-flow-advanced/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.

agentmods 80×15 button for react-flow-advanced

Your own site · 80×15
<a href="https://agentmods.dev/skills/existential-birds/beagle/react-flow-advanced"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/react-flow-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 16 Sept 2026
  • Snyk pass 16 Sept 2026
How audits are shown
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 5.1 $0.00042 $0.03248
Opus 5.5 $0.00017 $0.01299
Sonnet 5.5 $0.00008 $0.00650
Haiku 4.5 $0.00004 $0.00325

Measured 1mo ago against content hash 59b7506bd225, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

react-flow-advanced 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 1mo 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.

plugins/beagle-react/skills/react-flow-advanced/SKILL.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced React Flow Patterns

Gates (check before shipping)

Use these as sequenced checks—not “I think it works.”

  1. Sub-flows / groups: Pass: Every parentId matches an existing node id; the parent type is registered in nodeTypes; child positions are relative to the parent as intended (spot-check one drag inside/outside the group).
  2. Custom connection line: Pass: With a valid/invalid drag, stroke or connectionStatus visibly differs; path renders without console errors from getSmoothStepPath (invalid coords).
  3. External drag-and-drop: Pass: onDragOver always preventDefault(); drop position uses screenToFlowPosition (not raw clientX/clientY as flow coords); new node appears under the cursor on the pane.
  4. Undo/redo: Pass: One undo returns to the prior { nodes, edges }; redo restores; rapid changes do not leave canUndo/canRedo inconsistent with visible graph (exercise add → undo → redo once).
  5. Programmatic layout (dagre): Pass: After setNodes, node positions match intended rankdir; fitView runs after layout (e.g. requestAnimationFrame) so the viewport is not stale.
  6. Connect on drop (new node): Pass: Dropping on empty pane creates a node and an edge from the source handle; dropping on a valid target does not duplicate nodes (only the invalid-drop path adds a node).
  7. Selectors / store: Pass: Components that useStore with objects use shallow (or equivalent) so unrelated store updates do not re-render every frame.

Sub-Flows (Nested Nodes)

const nodes = [
  // Parent (group) node
  {
    id: 'group-1',
    type: 'group',
    position: { x: 0, y: 0 },
    style: { width: 400, height: 300, padding: 10 },
    data: { label: 'Group' },
  },
  // Child nodes
  {
    id: 'child-1',
    parentId: 'group-1',        // Reference parent
    extent: 'parent',           // Constrain to parent bounds
    expandParent: true,         // Auto-expand parent if dragged to edge
    position: { x: 20, y: 50 }, // Relative to parent
    data: { label: 'Child 1' },
  },
  {
    id: 'child-2',
    parentId: 'group-1',
    extent: 'parent',
    position: { x: 200, y: 50 },
    data: { label: 'Child 2' },
  },
];

Read the full file on GitHub · 441 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. 1mo ago First seen · 441 lines · 42 tokens per session scan A 59b7506bd225

Subscribe to this mod's changes

react-flow-advanced is a skill published in the GitHub repository existential-birds/beagle (82 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 3,248 once invoked, about $0.0002 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 2026-09-16.

Related

Other skills, from other repositories

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog-foss · 197 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog · 197 tokens

r-tidyverse-style

Use when the user asks to review or clean up R code for tidyverse style, standardize formatting or names, remove redundant comments or wrappers, or make a behavior-preserving style pass. Also use when writing substantial new R package code if the user requests tidyverse style or the package already follows it. Not for…

posit-dev/skills · 83 tokens

solid-principles

SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…

decebals/claude-code-java · 73 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens