markupr: Instructions file for Claude Code

CLAUDE.md

markupr CLAUDE.md is an instructions file for Claude Code from eddiesanjuan/markupr. It costs 2,979 tokens per session, scanned A, original, MIT.

Project instructions for markupR, a menu-bar app and command-line tool that records a developer’s screen and voice, then turns them into Markdown feedback with matching screenshots.

In plain words
What is it for?
Use them when changing the markupR desktop app, command-line tool, MCP server, or GitHub Action.
Why use it?
They give a coding agent the project’s structure, technologies, commands, and supported ways to work with recordings and feedback.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 markupr CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eddiesanjuan/markupr/claude-md"><img src="https://agentmods.dev/badge/instructions/eddiesanjuan/markupr/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,979 This file is loaded in full into every session.
When invoked 2,979 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 $0.02979 $0.02979
Opus 5 $0.01489 $0.01489
Sonnet 5 $0.00596 $0.00596
Haiku 4.5 $0.00298 $0.00298

Measured 8d ago against content hash 31dc05b776c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

markupr 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 8d 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 · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - markupR

Project Overview

markupR is a macOS/Windows menu bar app and CLI/MCP tool that intelligently captures developer feedback. It records your screen and voice simultaneously, then uses an intelligent post-processing pipeline to correlate transcript timestamps with the screen recording -- extracting the right frames at the right moments and stitching everything into a structured, AI-ready Markdown document. The output is purpose-built for AI coding agents: every screenshot placed exactly where it belongs, every issue clearly documented.

As of v2.5.0, markupR also ships as:

  • CLI tool (npx markupr analyze ./recording.mov) -- headless video analysis pipeline
  • MCP server (npx --package markupr markupr-mcp) -- Model Context Protocol server for AI coding agents (capture screenshots, analyze video, start/stop recordings)
  • GitHub Action (eddiesanjuan/markupr-action@v1) -- CI/CD visual feedback on PRs

Version: 2.6.0 License: MIT (Open Source)

Tech Stack

  • Framework: Electron + React + TypeScript
  • Build: electron-vite + Vite (desktop), esbuild (CLI/MCP)
  • Transcription: Local Whisper (default), OpenAI Whisper-1 API (optional cloud)
  • AI Analysis: Anthropic Claude API (BYOK or premium tier)
  • Testing: Vitest (unit, integration, e2e)
  • Package: electron-builder (DMG, NSIS, AppImage)
  • Styling: Tailwind CSS
  • Schema Validation: Zod
  • MCP: @modelcontextprotocol/sdk

Architecture

src/
├── main/                   # Electron main process
│   ├── index.ts            # Entry point, window management, IPC orchestration
│   ├── SessionController.ts # 7-state FSM with watchdog timer
│   ├── CrashRecovery.ts    # Auto-save every 5s, crash detection, recovery dialog
│   ├── ErrorHandler.ts     # Centralized error handling
│   ├── HotkeyManager.ts    # Global hotkey registration
│   ├── MenuManager.ts      # Application menu
│   ├── TrayManager.ts      # Menu bar tray icon and status
│   ├── PermissionManager.ts # macOS permission checks
│   ├── AutoUpdater.ts      # Auto-update via electron-updater
│   ├── ai/                 # AI analysis pipeline (Claude)
│   │   ├── AIPipelineManager.ts  # Orchestrates AI analysis (free/byok/premium tiers)
│   │   ├── ClaudeAnalyzer.ts     # Claude API integration
│   │   ├── ImageOptimizer.ts     # Screenshot optimization for API
│   │   ├── StructuredMarkdownBuilder.ts # AI-enhanced markdown output
│   │   └── types.ts              # AI pipeline types
│   ├── analysis/           # Feedback analysis and categorization
│   ├── audio/              # Microphone capture, VAD
│   ├── capture/            # Screen capture via desktopCapturer
│   ├── ipc/                # IPC handler registration and routing
│   ├── output/             # Document generation and export
│   │   ├── MarkdownGenerator.ts  # llms.txt-inspired markdown output
│   │   ├── ExportService.ts      # Multi-format export (MD, PDF, HTML, JSON)
│   │   ├── ClipboardService.ts   # Clipboard bridge (copies file path)
│   │   ├── FileManager.ts        # Session file management
│   │   └── sessionAdapter.ts     # Type conversion utilities
│   ├── pipeline/           # Post-processing pipeline
│   │   ├── PostProcessor.ts      # Pipeline orchestrator (transcribe -> analyze -> extract -> generate)
│   │   ├── TranscriptAnalyzer.ts # Heuristic key-moment detection
│   │   └── FrameExtractor.ts     # ffmpeg-based video frame extraction
│   ├── platform/           # Platform-specific code (Windows taskbar)
│   ├── settings/           # Persistent settings with secure API key storage
│   ├── transcription/      # Transcription tier management
│   │   ├── TierManager.ts       # Tier selection (Whisper, timer-only)
│   │   ├── WhisperService.ts     # Local Whisper integration
│   │   └── ModelDownloadManager.ts # Whisper model download from HuggingFace
│   └── windows/            # Window management (popover, taskbar)
├── cli/                    # Headless CLI tool
│   ├── index.ts            # CLI entry point (commander-based)
│   ├── CLIPipeline.ts      # Video analysis pipeline (ffmpeg + Whisper + markdown)
│   ├── WatchMode.ts        # Watch directory for new recordings
│   ├── doctor.ts           # System dependency checker (ffmpeg, Whisper, etc.)
│   └── init.ts             # Project config scaffolding (.markupr.json)
├── mcp/                    # MCP server for AI coding agents
│   ├── index.ts            # MCP entry point
│   ├── server.ts           # MCP server setup
│   ├── tools/              # MCP tool implementations
│   │   ├── analyzeScreenshot.ts  # Analyze a screenshot with Claude
│   │   ├── analyzeVideo.ts       # Analyze a video recording
│   │   ├── captureScreenshot.ts  # Capture a screenshot
│   │   ├── captureWithVoice.ts   # Capture with voice narration
│   │   ├── describeScreen.ts     # AI agents can see the user's screen
│   │   ├── pushToGitHub.ts       # Push feedback to GitHub Issues
│   │   ├── pushToLinear.ts       # Push feedback to Linear
│   │   ├── startRecording.ts     # Start a recording session
│   │   └── stopRecording.ts      # Stop a recording session
│   ├── session/            # MCP session management
│   ├── capture/            # MCP capture utilities
│   ├── utils/              # MCP utilities
│   ├── resources/          # MCP resource definitions
│   └── types.ts            # MCP type definitions
├── renderer/               # React UI
│   ├── App.tsx             # Main component with state machine UI
│   ├── AppWrapper.tsx      # Root wrapper with providers
│   ├── components/         # UI components
│   │   ├── AnnotationOverlay.tsx    # Drawing tools (arrow, circle, rect, freehand, text)
│   │   ├── AudioWaveform.tsx        # Real-time audio level visualization
│   │   ├── CrashRecoveryDialog.tsx  # Crash recovery UI
│   │   ├── DonateButton.tsx         # Rotating donate messages
│   │   ├── ModelDownloadDialog.tsx   # Whisper model download UI
│   │   ├── Onboarding.tsx           # First-run experience
│   │   ├── SessionHistory.tsx       # Session browser
│   │   ├── SessionReview.tsx        # Post-recording review/edit
│   │   ├── SettingsPanel.tsx        # Settings configuration
│   │   └── ...                      # Other UI components
│   ├── audio/              # Renderer-side audio capture bridge
│   ├── capture/            # Renderer-side screen recording (MediaRecorder)
│   └── hooks/              # React hooks (theme, animation)
├── preload/                # Context bridge (secure IPC)
└── shared/                 # Types shared between processes
    ├── types.ts            # IPC channels, payload types, state types
    └── hotkeys.ts          # Hotkey configuration types

Read the full file on GitHub · 232 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. 8d ago First seen · 232 lines · 2,979 tokens per session scan A 31dc05b776c3

Subscribe to this mod's changes

markupr CLAUDE.md is an instructions file published in the GitHub repository eddiesanjuan/markupr (18 stars, last pushed 4mo ago), licensed MIT. It adds 2,979 tokens to every session, about $0.0149 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.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

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