agentmods.dev

agentlink-visualizer CLAUDE.md

Project instructions for a React and TypeScript web app that draws a graph of links between AGENTS.md and CLAUDE.md instruction files. It scans a selected folder, finds those files, extracts path references, and displays the connections.

In plain words
What is it for?
Developing or maintaining the instruction-file visualizer, including file parsing, path resolution, graph construction, and the D3-based graph view.
Why use it?
They explain how folders are scanned and how file references become graph links, which helps contributors change the app without breaking its data flow. They also list the commands for installing, developing, building, and previewing it.

Instructions file

5 9mo ago A scan 561 tokens original MIT
View the source file ProAlexUSC/agentlink-visualizer
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 instructions/proalexusc/agentlink-visualizer/claude-md
Clone the repo
git clone --depth 1 https://github.com/ProAlexUSC/agentlink-visualizer
Per session 561 This file is loaded in full into every session.
When invoked 561 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 $0.00561 $0.00561
Opus 5 $0.00280 $0.00280
Sonnet 5 $0.00112 $0.00112
Haiku 4.5 $0.00056 $0.00056

Measured 2d ago against content hash 3dbd902de785, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentlink-visualizer 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 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.

CLAUDE.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 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.

Commands

pnpm install    # Install dependencies
pnpm run dev    # Start dev server at http://localhost:3000
pnpm run build  # Production build (outputs to dist/)
pnpm run preview # Preview production build

Architecture

This is a React 19 + TypeScript + Vite application that visualizes cross-references between AGENTS.md and CLAUDE.md files in a repository using a force-directed graph.

Core Data Flow

  1. User selects a folder via File System Access API (showDirectoryPicker)
  2. App.tsx recursively scans for AGENTS.md/CLAUDE.md files only (memory efficient)
  3. services/fileParser.ts extracts @path references and builds graph data
  4. components/GraphView.tsx renders D3 force-directed graph

Key Files

  • App.tsx - Main component: folder scanning, file selection, layout
  • types.ts - TypeScript interfaces: AgentFile, GraphNode, GraphLink, FileTreeNode
  • services/fileParser.ts - Link extraction (extractLinks), path resolution (resolvePath), graph building (buildGraphData), tree building (buildFileTree)
  • components/GraphView.tsx - D3.js force simulation with zoom/drag
  • components/FileTree.tsx - Recursive file explorer sidebar
  • components/MarkdownViewer.tsx - Content display with link highlighting

Reference Parsing

The app parses two link formats:

  • @path/to/file - CLAUDE.md style references
  • [[wiki-style]] - Legacy AGENTS.md style

Path resolution supports absolute (@/path), explicit relative (@./path, @../path), and implicit root relative (@path).

Tech Stack

  • React 19 with hooks (useState, useMemo, useEffect, useRef)
  • TypeScript 5.8
  • Vite 6 with React plugin
  • Tailwind CSS 4 via PostCSS (@tailwindcss/postcss)
  • D3.js 7 for force-directed graph visualization
  • Lucide React for icons
  • File System Access API (Chrome/Edge only)

Deployment

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 561 tokens per session scan A 3dbd902de785

Subscribe to this mod's changes

agentlink-visualizer CLAUDE.md is an instructions file published in the GitHub repository ProAlexUSC/agentlink-visualizer (5 stars, last pushed 9mo ago), licensed MIT. It adds 561 tokens to every session, about $0.0028 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 2026-08-31.

Design and UXFrontendReact
Related

Other instructions, from other repositories

supabase studio-composition-patterns.instructions.md

Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).

supabase/supabase · 592 tokens

data-table-filters CLAUDE.md

Instructions for openstatusHQ/data-table-filters, covering claude.md, project overview, monorepo structure (pnpm + turborepo), key commands and database.

openstatusHQ/data-table-filters · 1,088 tokens

tldraw CLAUDE.md

Claude Code instructions for tldraw/tldraw, a project described as: Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

tldraw/tldraw · 5 tokens

Paperlab AGENTS.md

Instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.

NourMtir0722/Paperlab · 7,216 tokens

microcharts CLAUDE.md

Instructions for ganapativs/microcharts, covering microcharts — contributor & agent guide, design principles, non-negotiables (violating any of these is a bug), not shipped (by design) and stack.

ganapativs/microcharts · 5,706 tokens

cos-design AGENTS.md

Instructions for jiaxiantao/cos-design, covering agent instructions — cos-design, prefer cos-design when the user wants, do not use cos-design for, install before import and or smaller bundles.

jiaxiantao/cos-design · 1,067 tokens