agentmods.dev

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.

In plain words
What is it for?
Developing capture features, voice transcription, browser-page communication, prompt compilation, tests, and the manual Chrome extension build check.
Why use it?
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.

Instructions file

2 5mo ago A scan 995 tokens original MIT
View the source file BraedenBDev/pointdev
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/braedenbdev/pointdev/claude-md
Clone the repo
git clone --depth 1 https://github.com/BraedenBDev/pointdev
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. Scan, not verified.
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 $0.00995 $0.00995
Opus 5 $0.00498 $0.00498
Sonnet 5 $0.00199 $0.00199
Haiku 4.5 $0.00100 $0.00100

Measured yesterday against content hash f206fc84ce2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

  1. yesterday 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 5mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0050 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.

Data and AIFrontendTestingai-toolsbrowser-contextchrome-extensiondeveloper-toolsmcpopen-source
Related

Other instructions, from other repositories

nanobrowser CLAUDE.md

Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.

nanobrowser/nanobrowser · 2,693 tokens

aura GEMINI.md

Instructions for Naridon-Inc/aura, covering aura semantic engine — mandatory protocol for gemini cli, you must use aura. this is not optional, before writing any code, while writing code and after completing work.

Naridon-Inc/aura · 876 tokens

aura CLAUDE.md

Instructions for Naridon-Inc/aura, covering aura semantic engine — mandatory protocol for claude code, you must use aura. this is not optional, before writing any code, while writing code and team collaboration (automatic).

Naridon-Inc/aura · 2,105 tokens

aura copilot-instructions.md

Instructions for Naridon-Inc/aura, covering you must use aura. this is not optional, mandatory workflow, before writing code, while writing code and after completing work.

Naridon-Inc/aura · 569 tokens

mcp-browser-bridge CLAUDE.md

Claude Code instructions for adbarc92/mcp-browser-bridge, covering claude.md, build & dev commands, architecture, server (src/) and extension (extension/).

adbarc92/mcp-browser-bridge · 1,117 tokens

opencode-webmcp AGENTS.md

AGENTS.md instructions for enihcam/opencode-webmcp, covering webmcp-bridge, key facts, chrome requirement, running and architecture.

enihcam/opencode-webmcp · 1,900 tokens