#claude-code

Roslyn-powered MCP server for AI-driven C# semantic analysis, refactoring, and code generation

Session management (ccd/ccr/ccs) and usage analytics (claude-code-usage) CLIs for Claude Code, plus three bundled skills (find-claude-code-session, move-session, claude-usage).

One rig, four tools for the whole dev loop. A family of single-binary CLIs that wrap your stack — from the inner build/test loop to changesets, releases, and your Claude Code setup. Native on macOS, Linux, and Windows. Change It, Ship It.

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.

Custom Telegram MCP server + TUI auto-responder for Claude Code — 10 MCP tools, SQLite message store, access control, reaction support

All-in-one engineering workflow & knowledge engine for Claude Code. One-command install, runs standalone (Node >=18, no bun). L0-L3 task classification, 13 runtime invariants, code review, browser QA, security audit, and a deduplicated knowledge base that compounds across tasks.

Measure AI coding agent token usage and estimate costs from local logs (Claude Code / Codex CLI) — zero dependencies, zero network

Sync Claude Code sessions across devices using Cloudflare R2 with end-to-end encryption

Keine Repository-Beschreibung veröffentlicht.

VMware NSX networking management: segments, gateways, NAT, routing, IPAM — 32 MCP tools

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

Agent Harness Tracker

MCP server multiplexer, configure all your MCP's in a single MCP with profiles, both TUI and web UI https://mcpmu.bigsy.uk/

Claude Code style auto-continue for OpenCode.

An AI workflow skill pack for research, competitions, and innovation projects.

🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it

One config. Every AI agent. Zero drift. Idempotent setup for OpenCode, Claude Code, Cursor, Windsurf, and Copilot.

Keine Repository-Beschreibung veröffentlicht.

Claude Code plugin that delegates code review, adversarial design critique, and isolated implementation to Kimi Code over the Agent Client Protocol (ACP). Security-first: Kimi works in an isolated workspace and hands back a Git patch.

Skill invocation runner: install an Agent Skill in a fresh fixture, invoke an agent harness headlessly, and report what actually reached the model, with transcript evidence.

Automate Ghidra reverse engineering from the command line — headless analysis, decompilation, and structured JSON output for AI agents like Claude Code

MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.

Compile portable coding-agent assets into target-native packages for Claude, Codex, Pi, Copilot, Grok, Cursor, and Antigravity CLI.

A cross-agent CLI your coding agent uses to delegate work. It gets back an answer, a review, or a patch — not the delegate's working context.

Go 微服务基础工具包（boot/log/mid/resp/store/registry/notify）— 内置 AI 辅助编程规范模板（Claude Code / Codex / Cursor / Windsurf / Copilot）

Portable Agent Skills for AI-assisted engineering workflows

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

Check quota/usage for AI coding CLI tools (Claude Code, OpenAI Codex, Google Gemini CLI, Z.AI). Auto-discovers credentials, auto-refreshes expired tokens, supports JSON output and compact one-liner format. Works on macOS and Linux.

cuttle is a browser for your agent. Websites do not block it. It keeps your logins. When a website asks for a person, you can take control. It works with playwright-cli, agent-browser and browser-use.

Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.