lens CLAUDE.md

Project instructions for RenderDraw Lens, a Chrome extension that lets developers mark up webpages for visual feedback and testing. They describe its code structure, build commands, and connection to Claude Code.

In plain words
What is it for?
Use them when developing the extension, running its checks, building the Chrome package, or working on its visual annotations, saved sessions, exports, and MCP bridge.
Why use it?
They give an agent the project-specific rules needed to change or build the extension consistently. Without them, the agent would need to infer how its parts fit together.

Instructions file

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/renderdraw/lens/claude-md
Clone the repo
git clone --depth 1 https://github.com/renderdraw/lens
Per session 838 This file is loaded in full into every session.
When invoked 838 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 $0.00838 $0.00838
Opus 5 $0.00419 $0.00419
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 2d ago against content hash 3013cda793a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lens 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 2d 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RenderDraw Lens

Chrome extension for universal visual feedback, video direction, and QA assertions across the RenderDraw stack.

Architecture

  • Manifest V3 Chrome extension with content script, service worker, side panel, and popup
  • Content Script (src/content/): Element selection engine, annotation popup, hover/click overlay
  • Service Worker (src/background/): Session persistence (IndexedDB), MCP message relay, tab capture
  • Side Panel (src/sidepanel/): Annotation list, project context, export (Markdown/JSON/Playwright/Remotion/clipboard)
  • Popup (src/popup/): Lens toggle, mode selector, side panel opener
  • MCP Bridge (src/mcp-bridge/): Standalone HTTP server (port 4848) for Claude Code integration
  • Shared (src/shared/): RAF schema, constants, storage, serializers

Build

npm install
npm run build       # Build extension to dist/
npm run dev         # Watch mode
npm run typecheck   # Type checking
npm run mcp         # Start MCP bridge server on port 4848

Load dist/ as an unpacked extension in Chrome (chrome://extensions → Developer mode → Load unpacked).

Build System

Vite with inlineContentScript plugin. Post-build, shared chunk imports are inlined into content.js (wrapped in IIFE) and background.js because Chrome MV3 content scripts don't support ES module imports.

RAF Schema

All annotations use the RenderDraw Annotation Format (RAF) defined in src/shared/raf-schema.ts. Three modes:

  • Feedback: Visual bug reports with element selection, computed styles, component trees
  • Video Direction: Cinematic sequences with actions (zoom, pan, highlight), timing, narration
  • QA Assertion: Visual regression specs with Playwright selectors and expected values

Styling

All UI uses the Journeys dark theme: #0a0a0f background, #FFD700 gold accents, #14B8A6 teal secondary, DM Sans typography. Design tokens in src/shared/constants.ts.

Content Script Injection

Content scripts auto-inject on new page loads via manifest.json. For pages open before extension install, both the popup and service worker use chrome.scripting.executeScript() as a fallback — try messaging, catch the error, inject programmatically, retry.

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 838 tokens per session scan A 3013cda793a2

Subscribe to this mod's changes

lens CLAUDE.md is an instructions file published in the GitHub repository renderdraw/lens (4 stars, last pushed 5mo ago), licensed MIT. It adds 838 tokens to every session, about $0.0042 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.