Borrowing it
Nothing to install: this file belongs to soumyachk101/VibeLens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/soumyachk101/VibeLens/main/CLAUDE.mdgit clone --depth 1 https://github.com/soumyachk101/VibeLensWrote 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/instructions/soumyachk101/vibelens/claude-md)<a href="https://agentmods.dev/instructions/soumyachk101/vibelens/claude-md"><img src="https://agentmods.dev/badge/instructions/soumyachk101/vibelens/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.
<a href="https://agentmods.dev/instructions/soumyachk101/vibelens/claude-md"><img src="https://agentmods.dev/badge/instructions/soumyachk101/vibelens/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03022 | $0.03022 |
| Opus 5 | $0.01511 | $0.01511 |
| Sonnet 5 | $0.00604 | $0.00604 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
VibeLens 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 10d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working on VibeLens
Guidance for AI coding assistants (Claude Code, Cursor, Antigravity, Copilot) contributing to this repository. Read this before editing.
What this project is
VibeLens is an MCP server that gives an AI coding assistant vision into a
locally running web app. It exposes exactly one tool, inspect_localhost_ui,
which returns a screenshot, console/network diagnostics, and a token-optimized
DOM snapshot in a single call.
It is a developer tool that runs on the user's own machine and drives a real browser. That makes correctness around security and resource cleanup more important than features.
Stack
- Node.js ≥ 20, ESM only (
"type": "module"). Playwright 1.62 requires >=20 and vitest 4 supports ^20 || ^22 || >=24, so 20 is the floor. - TypeScript,
strict(plusnoUncheckedIndexedAccess) @modelcontextprotocol/sdk— MCP server + stdio transportplaywright— headless Chromiumzod— tool input schemavitest— tests
Dependencies are pinned exactly. Do not add a dependency without a concrete reason; do not swap Playwright for Puppeteer.
Architecture
src/index.ts Executable entrypoint (#!/usr/bin/env node). Connects the
server to StdioServerTransport. Deliberately thin.
src/server.ts MCP server: tool schema, description, response assembly,
error formatting. No side effects on import.
src/browser.ts Playwright capture engine: launch → observe → capture → close.
src/dom.ts sanitizeDomInPage() runs INSIDE the browser; truncateDom()
runs in Node.
src/security.ts validateLocalUrl() — the SSRF allowlist.
src/types.ts Shared types, VIEWPORT_PRESETS, LIMITS, CaptureError.
Data flow: server.ts → captureUIState() → { image, diagnostics, dom } →
two MCP content blocks (image first, then text).
Invariants — do not break these
- stdout belongs to the MCP transport. Never
console.log. Use thelog()helper inserver.ts, which writes to stderr. A stray stdout write corrupts the JSON-RPC stream and silently breaks the integration. - The browser is always closed in a
finallyblock. A leaked Chromium costs hundreds of MB and the server is long-lived. - Validate the URL before launching anything.
validateLocalUrl()is the only gate against SSRF. Never add a bypass, an "allow any host" flag, or DNS resolution of arbitrary hostnames (that reintroduces DNS rebinding). Instance-metadata addresses stay unconditionally blocked. - A failed capture must never crash the process. Catch, wrap in
CaptureError, return{ isError: true, content: [text] }. - Every error the model sees needs a next step.
CaptureErrorcarries both amessage(what happened) and ahint(what to do). Keep that contract. - Respect the token budget. Everything in
LIMITSexists to protect the caller's context window. Raising a limit needs justification; adding a new unbounded field to the payload is not acceptable. sanitizeDomInPagemust stay self-contained. Playwright serializes it withFunction.prototype.toString(), so it cannot reference imports or module-scope variables — configuration arrives via its single argument.- The tool stays read-only. It observes pages. It does not click, type, navigate the user's app into a mutating state, or write files.
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.
- 10d ago First seen · 240 lines · 3,022 tokens per session scan A 85ed19f58219
VibeLens CLAUDE.md is an instructions file published in the GitHub repository soumyachk101/VibeLens (0 stars, last pushed 3d ago), licensed MIT. It adds 3,022 tokens to every session, about $0.0151 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.