MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
AI Shipping Kit — for PMs and founders accountable for AI-built code. Document a vibe-coded app, review it for correctness, security and performance defects, and produce a reviewer-ready shipping packet.
Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContex.
Local, metadata-only telemetry for Claude Code. A bundled observer records session, tool, and subagent lifecycle events into SQLite on your machine, an optional statusline shows live context and usage, and an OpenTelemetry Collector forwards redacted signals to the observer. Logs reach configured sinks, including…
This skill should be used when the user asks to "upload images to Cloudflare", "implement direct creator upload", "configure image transformations", "optimize WebP/AVIF", "create image variants", "generate signed URLs", "add image watermarks", "integrate with Next.js/Remix", "configure webhooks", "debug CORS errors"…
Claude Code plugin — 41 tools, 45 skills, 13 agents. Currency Guard keeps Claude on current docs, not stale training data. Elite SEO strategy with AI traffic tracking, IndexNow, GSC-GA4 cross-reference, CTR anomalies, brand filtering, keyword intelligence, index doctor, codebase index, pentest, ship, launch, grow…
★not rated 123 3mo agoA
tokens not measured
originalMIT
The AI-native PM operating system — deep, framework-grounded PM skills with live MCP tool integrations, chained sub-agent workflows, and persistent user memory. Built for solo PMs and founding PMs who need an AI partner that actually knows their product.
Audit and optimize your Claude Code configuration. Caches current Claude Code ecosystem knowledge so any subsequent agent task — building a skill, configuring an MCP, authoring CLAUDE.md — can read it instead of re-fetching docs.
★not rated 46 4mo agoA
tokens not measured
originalMIT
Automates macOS apps via Apple Events using AppleScript (discovery) and JXA (production logic). Use when asked about AppleScript, JXA, osascript, or macOS app automation.
★not rated 45 1mo agoA
tokens not measured
originalMIT
Thinking discipline for AI work. Clarify intent, shape approach, consult experts, guard unsupervised work, hand work back so you own it. The slop hook needs CLAUDECODEENABLEFUNCTIONHOOKS=1.
A workflow for writing Korean job-application personal statements, known as self-introduction letters. It covers company research, drafting, length adjustment, expert review, editing, and final checks for applications to multiple employers.
★not rated 22
changed 16d agoA
tokens not measured
originalMIT
Developer tooling setup and management (SOPS secrets encryption, Claude Code environment setup, multi-ecosystem quality stack for JVM/Node.js/Python, Taskfile task runner setup and audit, Tilt local Kubernetes development setup and audit, browser-companion live-preview server with cross-plugin arkhe-preview CLI).
★not rated 21
changed todayA
tokens not measured
originalMIT
Audio feedback system with multilingual TTS announcements, AI-powered contextual messages, and sound effects for Claude Code. Transform your coding experience with intelligent voice feedback that keeps you informed without breaking your flow.
★not rated 19 8mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: