$ show cordwainersmith/Claudoscope
Claudoscope is a native macOS menu-bar application that serves as an observability and configuration management dashboard for Claude Code, Anthropic's AI coding assistant. It reads local Claude Code session transcripts (JSONL), caches parsed summaries in a GRDB-backed SQLite store, and presents analytics on token usage, cost, cache effectiveness, model distribution, and attribution per skill, MCP tool, or agent. The app also includes a comprehensive configuration linter (100+ rules for security, skills, hooks, routing, hardening, and more), an installer for Claude Code hardening baselines and agent routing stacks, real-time file monitoring via FSEvents, and an optional MCP server that exposes read-only tools for AI-driven querying. It operates as a background agent with a menu bar popover and a full dashboard window. The application is built as a monolithic SwiftUI macOS app with modular service actors, extensive unit tests (60+ test files), and a clean separation of concerns. Key entry points include the session parser, analytics engine, linter service, and installer file operations. It depends on Claude Code's local file structure and specific JSONL schemas, which drives a medium technical drift risk as those formats evolve. The codebase demonstrates high craftsmanship with reusable patterns such as pure analytic functions, atomic configuration writers, and a design token system, making it a strong example of a well-engineered developer tool.
The LLM identified 4 files worth highlighting for reuse:
A pure-function YAML frontmatter parser for markdown files. It extracts key-value metadata from between `---` delimiters and is used to parse skill, command, and plugin definitions. The component is self-contained (no internal module imports), thread-safe, and can be extracted into any project that needs to parse frontmatter from Markdown or text files.
A stateless cost alert evaluation engine that implements a doubling-ladder re-alert strategy, episode reset, and per-day/month rolling-window checks. It takes a `SpendLedger` and thresholds and returns alert actions. It does not depend on any UI or service layer, making it easily reusable in any cost tracking system that needs configurable alert escalation.
A pure computation engine that aggregates session summaries into analytics data (daily cost, model breakdown, cache effectiveness, latency/effort distributions). It takes arrays of session summaries and pricing tables and returns structured analytics, with no dependencies on stores or UI. The algorithm is well-documented and can be reused in any project needing similar usage statistics from event logs.
A utility for atomic file writes, backup creation, marker block appending/stripping, SHA256 hashing, and dictionary merging. It is used by all installers (hardening, routing, notification hooks) to safely modify user configuration. The operations are isolated and generic, making it reusable for any macOS application that needs to surgically modify config files with rollback safety.