Browse the directory

A Claude Code statusline that reads prompt-cache token metrics from session JSON and renders a color-coded hit-rate bar with an estimated token-savings readout.

Open-source semantic cache for LLM applications that stores and reuses model responses through embedding similarity to cut API cost and latency, with modular embedding, vector-store, cache-storage, and eviction components.

Expert prompt caching cost audit capability pack for measuring Claude Code cache hit rates, identifying cache invalidation triggers, and reducing token spend from CLAUDE.md edits, model switches, and startup load changes.

Local code indexing MCP server that lets AI assistants search repositories, build symbol indexes, inspect file summaries, monitor changes, and navigate multi-language codebases.

Document intelligence MCP server for extracting text, metadata, OCR output, structured data, embeddings, chunks, cache state, and supported-format information from PDFs, Office files, images, code, and many other formats.

MCP server for live NixOS, nixpkgs, Home Manager, nix-darwin, Nixvim, FlakeHub, Noogle, NixOS Wiki, nix.dev, NixHub, binary cache, and local flake input lookups.

Local code-search MCP server for agents, using CPU-only hybrid retrieval to index repositories and return focused snippets for natural-language queries.

Build React server-state workflows with TanStack Query v5, including query keys, QueryClient setup, cache defaults, mutations, invalidation, hydration, retries, and privacy-aware data handling.

A practical walkthrough of token and spend accounting in the Claude Agent SDK. Read total_cost_usd from the result message, deduplicate parallel tool calls that share an assistant id, break spend down per model with modelUsage, sum cost across query() calls yourself, and read cache_creation/cache_read tokens.

Source-backed agent that reduces token cost and latency in Claude Code by improving prompt-cache hit rates, advising on stable context ordering, lean CLAUDE.md, on-demand skills, and MCP tool-search, grounded in the official docs.

Claude Code session health aggregator providing A-F grade based on cost efficiency, latency performance, productivity velocity, and cache utilization with actionable recommendations.

Cleans up temporary files, caches, and resources when Claude session ends. This Stop hook provides comprehensive environment cleanup for development projects, automatically removing temporary files, build artifacts, cache directories, and system-specific files across multiple platforms.

Automatically clears relevant Redis cache keys when data model files are modified.

Official Redis MCP server providing natural language interface for Redis data management and operations

Troubleshoot Claude Code prompt caching: cache invalidation triggers, prefix stability, cost spikes, and verifying cache hits during long sessions.

Expert OpenNext + Cloudflare capability skill for Next.js on Workers, runtime constraints, cache strategy, and production-safe deploy architecture.