agentmods.dev

underpixel: Instructions file for Claude Code

CLAUDE.md

underpixel CLAUDE.md is an instructions file for Claude Code from Leluth/underpixel. It costs 457 tokens per session, scanned A, original, MIT.

Project instructions for UnderPixel, a monorepo containing a Chrome extension, a local bridge server, and shared packages. A monorepo is one repository that contains several related projects.

In plain words
What is it for?
Use them when developing UnderPixel, especially when installing dependencies, building packages, running tests or linting, or changing network capture and shared types.
Why use it?
They document the project’s build, test, and design conventions, including details that are easy to break when changing browser or server code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Leluth/underpixel's own configuration. It tells Claude Code how to work on underpixel 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 underpixel configures →

not rated 0repo 6mo ago A scan 457 tokens original MIT
View source ↗ Leluth/underpixel
Reuse

Borrowing it

Nothing to install: this file belongs to Leluth/underpixel. 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/Leluth/underpixel/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Leluth/underpixel

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 underpixel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leluth/underpixel/claude-md/github.svg)](https://agentmods.dev/instructions/leluth/underpixel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/leluth/underpixel/claude-md"><img src="https://agentmods.dev/badge/instructions/leluth/underpixel/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 underpixel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/leluth/underpixel/claude-md"><img src="https://agentmods.dev/badge/instructions/leluth/underpixel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 457 This file is loaded in full into every session.
When invoked 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00457 $0.00457
Opus 5.5 $0.00183 $0.00183
Sonnet 5.5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured 2mo ago against content hash dce510bf650c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

underpixel 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 · 34 lines

What it actually says

UnderPixel

Chrome extension + MCP server for visual-API correlation. Monorepo: extension/ (Chrome MV3, WXT), bridge/ (Native Messaging + Fastify MCP server), packages/shared/ (types, constants, tool schemas).

Commands

pnpm install          # from root
pnpm build            # builds all (shared → bridge → extension)
pnpm dev              # WXT dev mode with HMR
pnpm test             # vitest across all packages
pnpm lint             # ESLint
pnpm format:check     # Prettier check

Workflow

  • Run pnpm lint and pnpm test before reporting done.
  • Don't commit/push unless explicitly asked.

Non-obvious conventions

  • Network capture requires chrome.debugger (CDP) — chrome.webRequest cannot read response bodies.
  • rrweb runs in MAIN world content script, bridged to ISOLATED world via window.postMessage — rrweb needs real DOM access but chrome.runtime only works in ISOLATED world.
  • Response bodies stored inline if <100KB, otherwise in separate responseBodies IDB store via responseBodyRef. Don't change these thresholds without updating both capture.ts and api_calls tool.
  • Don't modify packages/shared/src/types.ts lightly — both extension and bridge depend on it.
  • Replay UI uses Svelte 5 in legacy mode (Svelte 4 syntax). If migrating to runes, convert all components in one pass.
  • Svelte 4 store caveat — $store.anyProp subscribes to the entire store. Avoid reading $replayStore in reactive blocks that don't need currentTime (fires at 60Hz).
  • rrweb inlineImages: false — broken in this alpha (rrweb-io/rrweb#1218). Causes seek crashes on cross-origin-heavy pages. Enable when fixed.

Design docs

See docs/ — includes high-level vision, tech design, and per-feature specs/plans in docs/superpowers/.

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. 2mo ago First seen · 34 lines · 457 tokens per session scan A dce510bf650c

Subscribe to this mod's changes

underpixel CLAUDE.md is an instructions file published in the GitHub repository Leluth/underpixel (0 stars, last pushed 6mo ago), licensed MIT. It adds 457 tokens to every session, about $0.0018 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.

Claude Codeapi-monitoringbrowser-automationchrome-extensiondeveloper-toolsdevtools
Related

Other instructions, from other repositories

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 · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens