agentmods.dev

ui-debugger-mcp: Instructions file for Claude Code

CLAUDE.md

ui-debugger-mcp CLAUDE.md is an instructions file for Claude Code from developerz-ai/ui-debugger-mcp. It costs 4,447 tokens per session, scanned B, original, MIT.

Project instructions for an MCP server that lets an AI agent debug a user interface autonomously. One agent sets goals and fixes code, while other agents drive the target and inspect screenshots.

In plain words
What is it for?
Use it when developing or maintaining the UI debugger MCP server, including its Bun and TypeScript code, agent loop, browser sessions, and response style.
Why use it?
UI testing often requires repeated browser interaction and visual checking. These instructions define how the server, its agents, sessions, and responses should work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

This is developerz-ai/ui-debugger-mcp's own configuration. It tells Claude Code how to work on ui-debugger-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ui-debugger-mcp configures →

not rated 2repo changed 8d ago B scan 4,447 tokens original MIT
View source ↗ developerz-ai/ui-debugger-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to developerz-ai/ui-debugger-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/developerz-ai/ui-debugger-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/ui-debugger-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.

agentmods badge for ui-debugger-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/developerz-ai/ui-debugger-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/developerz-ai/ui-debugger-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/developerz-ai/ui-debugger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ui-debugger-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.

agentmods 80×15 button for ui-debugger-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/developerz-ai/ui-debugger-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ui-debugger-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,447 This file is loaded in full into every session.
When invoked 4,447 The same file — it is already loaded in full.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04447 $0.04447
Opus 5.5 $0.01779 $0.01779
Sonnet 5.5 $0.00889 $0.00889
Haiku 4.5 $0.00445 $0.00445

Measured 8d ago against content hash 55fd2d75dc8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ui-debugger-mcp CLAUDE.md scanned grade B with 1 finding 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 8d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- `.mcp.json` — how to LAUNCH server (command, model API key + base url). Gitignored. Secret.
CLAUDE.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Debugger MCP

Bun · TypeScript · Vercel AI SDK · OpenAI-compatible router (OpenRouter default). MCP server that debugs UIs autonomously.

Smart agent hands a goal (a "story") to a small fast agent inside this server. The small agent drives the target, gathers evidence, reports findings. Smart agent fixes code, asks again. Loop until the UI works. No human clicking.

Goal: stuff WORKS + LOOKS NICE. Three actors (docs/idea/models.md):

  • smart agent — the boss (Claude/caller): sets goals, fixes code, loops.
  • fast guy — the driver (fast, text-only, blind): controls the target.
  • vision guy — the eyes (multimodal): describes screenshots, judges looks.

Response Rules

  • Execute. No preamble.
  • Lead with action or answer.
  • Terse. Fragments OK.

What this is

  • MCP server (stdio). Ships as npm package, run via npx/bunx.
  • The agent brain runs inside the server (Vercel AI SDK). Not the caller's.
  • Session keyed by current dir (cwd). One project = one session.
  • One debug run at a time (persistent Chrome profile locks the profile).

Reference repos (read for patterns, don't copy blind)

  • ../ai-task-master — build template: Bun + TS + Vercel AI SDK, subagent-as-tool, MCP, Zod, Biome.
  • ../gold-standards-in-ai/docs — house rules: few fat tools, SRP, custom errors, compressed config.
  • ../../sebyx07/claude-code-bible/docs — deeper handbook. ?debug-ai=true login bypass pattern.

Architecture

  • src/main.ts — CLI entry (help/version/init/status/stop).
  • src/boot.ts — server boot: owner-lock gate → config → workspace → provider/models → stdio MCP server.
  • src/mcp/ — MCP server, tool defs (few fat tools, NOT one-per-action).
  • src/agent/ — debug agent (Vercel AI SDK loop). The fast guy (driver) + the vision guy (eyes via look). Models per role via OpenAI-compatible router (OpenRouter default). Defaults: deepseek (text), qwen (image).
    • prompts/ — OUR system prompts: in-repo, versioned, tested, provider-agnostic. NEVER rely on a 3rd-party model's defaults. Written compressed — they are resent every step (../../sebyx07/claude-code-bible/docs/11-compressed-config.md).
  • src/adapters/ — target control behind one shared contract.
    • browser/ — web via CDP (headless default). ✅ shipped.
    • desktop/ — X11/Wayland windows. Covers desktop app AND mobile emulator. ✅ shipped.
    • android/ — ADB + uiautomator. ✅ shipped.
  • src/session/ — cwd-keyed session, per-project workspace, state.
  • src/config/ — load the project config (.dz/ui-debugger/ui-debugger-mcp.json first, root .ui-debugger-mcp.json fallback), resolve model/targets.
  • src/services/ — business logic. Thin handlers, logic here.
  • src/errors.ts — custom error classes (base UiDebuggerError + ConfigError / AdapterError / AuthError / AgentError / WorkspaceError / ProviderError / etc.). No generic Error.

Read the full file on GitHub · 312 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. 8d ago Changed · +6 lines · +132 tokens per session 55fd2d75dc8d
  2. 9d ago Changed · +26 lines · +401 tokens per session ad25ba70af16
  3. 11d ago Changed · +24 lines · +381 tokens per session 4b4c1585a410
  4. 1mo ago Changed · +3 lines · +57 tokens per session db18f69ace25
  5. 2mo ago Changed · +6 lines · +111 tokens per session 227cee992404
  6. 2mo ago First seen · 247 lines · 3,365 tokens per session scan B a765d5d23b7a

Subscribe to this mod's changes

ui-debugger-mcp CLAUDE.md is an instructions file published in the GitHub repository developerz-ai/ui-debugger-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 4,447 tokens to every session, about $0.0178 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DebuggingFrontendai-agentsbrowser-automationbuncdpdesktop-automationmcp
Related

ui-debugger-mcp CLAUDE.md compared with instructions from other repositories

ui-debugger-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ui-debugger-mcp CLAUDE.mddeveloperz-ai/ui-debugger-mcpInstructions file2yesterdayMITB4,447Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode