agentmods.dev

layrr: Instructions file for Claude Code

CLAUDE.md

layrr CLAUDE.md is an instructions file for Claude Code from narnia-sh/layrr. It costs 326 tokens per session, scanned A, original, MIT.

A guide for Layrr, a command-line tool that connects a local development server to an AI-assisted browser editing workflow. It describes the proxy, browser overlay, source-code mapping, edit queue, and supported agents.

In plain words
What is it for?
Use it when building Layrr, running its CLI, changing the browser overlay, mapping screen selections to source lines, or integrating Claude Code, Codex, or Gemini.
Why use it?
It clarifies the project’s intentionally limited scope and identifies where each part of the editing process is implemented. This helps avoid adding hosted-dashboard features that are outside the project.

Instructions file for Claude Code

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

This is narnia-sh/layrr's own configuration. It tells Claude Code how to work on layrr 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 layrr configures →

not rated 264repo +1 3mo ago A scan 326 tokens original MIT
View source ↗ narnia-sh/layrr layrr.dev
Reuse

Borrowing it

Nothing to install: this file belongs to narnia-sh/layrr. 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/narnia-sh/layrr/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/narnia-sh/layrr

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 layrr CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/narnia-sh/layrr/claude-md.svg)](https://agentmods.dev/instructions/narnia-sh/layrr/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/narnia-sh/layrr/claude-md"><img src="https://agentmods.dev/badge/instructions/narnia-sh/layrr/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 326 This file is loaded in full into every session.
When invoked 326 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00326 $0.00326
Opus 5 $0.00163 $0.00163
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00033 $0.00033

Measured 7d ago against content hash e0f26d5e785f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

layrr 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 7d 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 · 45 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

Scope

Layrr is kept as a CLI-only project. The hosted dashboard, process manager, deployment files, templates, and hosted-only agents are intentionally removed.

The repository root is the CLI package.

Commands

pnpm install
pnpm build

Local CLI run after building:

node dist/cli.js --port 3000

There are no automated tests configured.

CLI Architecture

The CLI proxies a local dev server, injects a browser overlay, resolves selected elements back to source code, sends edit requests to an AI agent, and records successful edits in git.

Important paths:

  • src/cli.ts - argument parsing, agent selection, git preflight, proxy startup, edit loop
  • src/agents/ - public agent integrations for Claude Code, Codex, and Gemini via Pi
  • src/server/ - HTTP proxy, WebSocket handling, edit queue, version history
  • src/editor/source-mapper.ts - source file and line resolution
  • overlay/ - injected browser UI, bundled as an IIFE
  • scripts/build.ts - builds overlay, compiles TypeScript, copies font assets

Notes

  • Public agents are claude, codex, and gemini.
  • Keep overlay CSS scoped with the __layrr prefix.
  • Do not reintroduce app/server/dashboard/deployment code unless explicitly requested.
  • Use rg for repository searches.
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. 7d ago First seen · 45 lines · 326 tokens per session scan A e0f26d5e785f

Subscribe to this mod's changes

layrr CLAUDE.md is an instructions file published in the GitHub repository narnia-sh/layrr (264 stars, last pushed 3mo ago), licensed MIT. It adds 326 tokens to every session, about $0.0016 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 2026-08-30.

Browser automationClaude CodeFrontendagentaiai-agentbrowser-coding-agentclaude
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens