Dynamic Shell Command MCP Server

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

Shell and coding agent on mcp clients

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

pty-mcp-server

LSP plugins for Claude Code — Bash/Shell, C/C++/Objective-C, C#, Clojure, Dart/Flutter, Elixir, Gleam, Go, Java, Kotlin, Lua, Nix, OCaml, PHP, Python, Ruby, Rust, Swift, Terraform, TypeScript/JavaScript, YAML & Zig

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Claude Code, Gemini CLI, Hermes, OpenClaw.

MCP implementation of Claude Code capabilities and more

Give any AI agent the ability to code

Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td

Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

Token-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Write-time code quality enforcement system for Claude Code. Every file edit triggers automated formatting and linting through fast Rust-based linters and dedicated Claude instances that intelligently fix remaining violations

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.