What is pointdev CLAUDE.md?

Project instructions for PointDev, an open-source Chrome extension that captures browser selections, voice notes, drawings, and cursor actions, then turns them into prompts for AI coding agents.

Developing capture features, voice transcription, browser-page communication, prompt compilation, tests, and the manual Chrome extension build check.

They explain how the extension's side panel, background worker, content scripts, and compiled output share captured information, making changes less likely to break another part.

How BraedenBDev/pointdev configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to BraedenBDev/pointdev. 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/BraedenBDev/pointdev/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/BraedenBDev/pointdev

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/braedenbdev/pointdev/claude-md/github.svg)](https://agentmods.dev/instructions/braedenbdev/pointdev/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/braedenbdev/pointdev/claude-md"><img src="https://agentmods.dev/badge/instructions/braedenbdev/pointdev/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/braedenbdev/pointdev/claude-md"><img src="https://agentmods.dev/badge/instructions/braedenbdev/pointdev/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 995 This file is loaded in full into every session.

When invoked 995 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	$0.00995	$0.00995
Opus 5.5	$0.00398	$0.00398
Sonnet 5.5	$0.00199	$0.00199
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash f206fc84ce2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pointdev 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

PointDev is an open source Chrome extension (MV3) that captures structured browser context — element selection, voice narration, canvas annotations, cursor behavior — and compiles it into structured prompts for AI coding agents. Built with React 18 + TypeScript, Vite, bun.

Commands

bun install          # Install dependencies
bun dev              # Start Vite in watch mode (load dist/ as unpacked extension)
bun build            # Production build
bun run test         # Run Vitest unit tests (NOT `bun test` — that invokes Bun's runner)
bun run test:watch   # Vitest watch mode
bun lint             # ESLint + Prettier check

Extension testing is manual: load unpacked from dist/ in chrome://extensions/ (Developer Mode).

Architecture

Four cooperating MV3 contexts:

Sidepanel (src/sidepanel/) — React UI. Capture controls, live feedback, compiled output, copy-to-clipboard. Runs Web Speech API for voice transcription.
Service Worker (src/background/) — State coordinator. Holds CaptureSession, routes messages between sidepanel and content script. Kept alive via port connection during capture, backed by chrome.storage.session.
Content Script (src/content/) — Injected into active tab. Element selector, canvas annotation overlay (position: fixed), cursor tracker, React fiber inspector.
Shared (src/shared/) — Types (types.ts), message definitions (messages.ts), template formatter (formatter.ts).

Message flow: Sidepanel ↔ Service Worker ↔ Content Script (via chrome.runtime messaging + port connection).

Key Technical Details

Canvas overlay uses position: fixed (viewport-sized), coordinates converted to page-relative on mouse release
Web Speech API runs in sidepanel context — high-risk assumption, validated early. Fallback: offscreen document.
React component detection is opportunistic (reads __reactFiber$ from DOM nodes). Graceful fallback to CSS selector.
Service worker can terminate in MV3. Long-lived port from sidepanel prevents this. Recovery via chrome.storage.session.
Content script injection guarded by PING/PONG to prevent duplicates.
CSS selectors generated via css-selector-generator package.

Read the full file on GitHub · 101 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 · 101 lines · 995 tokens per session scan A f206fc84ce2f

Subscribe to this mod's changes

pointdev CLAUDE.md is an instructions file published in the GitHub repository BraedenBDev/pointdev (2 stars, last pushed 1mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0040 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.

ai-tools browser-context chrome-extension developer-tools mcp open-source

pointdev CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pointdev CLAUDE.mdBraedenBDev/pointdev	Instructions file	2	1mo ago	MIT	A	995	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

pointdev: Instructions file for Claude Code