What is why-did-you-render-mcp CLAUDE.md?

Project instructions for an MCP server, a tool that lets coding agents exchange information with other programs, about why-did-you-render-mcp. The server reports unnecessary React user-interface redraws from browser projects so agents can investigate them.

It is for understanding the server's packages, browser connections, real-time render reports, shared files, and design choices.

It gives developers a shared explanation of the server's design, including how several running copies communicate and where their captured data is stored.

How 0x1f320/why-did-you-render-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 0x1f320/why-did-you-render-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/0x1f320/why-did-you-render-mcp/dev/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/0x1f320/why-did-you-render-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/0x1f320/why-did-you-render-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/0x1f320/why-did-you-render-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/0x1f320/why-did-you-render-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0x1f320/why-did-you-render-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/0x1f320/why-did-you-render-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0x1f320/why-did-you-render-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,457 This file is loaded in full into every session.

When invoked 3,457 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03457	$0.03457
Opus 5.5	$0.01383	$0.01383
Sonnet 5.5	$0.00691	$0.00691
Haiku 4.5	$0.00346	$0.00346

Measured 2mo ago against content hash c7ec098f65d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

why-did-you-render-mcp 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 2mo 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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

why-did-you-render-mcp

An MCP (Model Context Protocol) server that bridges why-did-you-render data from the browser to coding agents. It captures unnecessary React re-render reports in real time and exposes them as MCP tools, so agents can diagnose and fix performance issues without manual browser inspection.

Architecture

Browser (project-a) ──┐
Browser (project-b) ──┤
                      ▼
                MCP #1 → WS(:4649) ✅ (first instance binds, "owner")
                MCP #2 → WS(:4649) ❌ → relay client ──▶ MCP #1
                      │
                      ▼
               ~/.wdyr-mcp/
               ├─ renders/  (JSONL files, shared across instances)
               │  ├─ http___localhost_3000.jsonl
               │  └─ http___localhost_5173.jsonl
               └─ snapshots/  (JSON files, named snapshots)
                  └─ before-fix.json

Multiple MCP instances can run simultaneously. Only the first instance (the "owner") binds the WebSocket server; others gracefully skip via EADDRINUSE handling and instead connect as socket.io clients to the owner for relaying commands (e.g. pause/resume). All instances read/write the same JSONL files.
Multi-project support — Each project is identified by the browser's location.origin (e.g. http://localhost:3000). Render data is stored in per-project JSONL files under ~/.wdyr-mcp/renders/.
Project disambiguation — When only one project exists, tools auto-select it. When multiple exist, tools return a message instructing the agent to ask the user for their dev server URL.

Packages

This is a pnpm workspace monorepo with three packages:

@0x1f320.sh/why-did-you-render-mcp (packages/server/) — MCP server (Node.js). Published to npm.
@0x1f320.sh/why-did-you-render-mcp-client (packages/client/) — Browser client. Published to npm independently, so users can install it without server dependencies.
@why-did-you-render-mcp/types (packages/types/) — Shared type definitions. Private, internal-only (not published). Both client and server depend on it via workspace:*.

Read the full file on GitHub · 150 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.

2mo ago First seen · 150 lines · 3,457 tokens per session scan A c7ec098f65d9

Subscribe to this mod's changes

why-did-you-render-mcp CLAUDE.md is an instructions file published in the GitHub repository 0x1f320/why-did-you-render-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 3,457 tokens to every session, about $0.0138 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 2026-08-31.

Debugging Frontend React devtools mcp performance websocket

why-did-you-render-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
why-did-you-render-mcp CLAUDE.md0x1f320/why-did-you-render-mcp	Instructions file	1	7mo ago	MIT	A	3,457	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

why-did-you-render-mcp: Instructions file for Claude Code