Collection · 21 entries
Claude Code tools, plugins, and integrations
The best tools, MCP servers, and harnesses for getting more out of Claude Code - orchestration, observability, telemetry, and remote control.
Claude Code is the largest cluster in this directory for a reason: most of the interesting work in coding agents right now happens around it. The picks below cover orchestration (multi-agent harnesses, parallel runners), observability (token cost, session monitors, live agent views), security (sandboxes, scrubbers, governance), and remote control (Telegram, Slack, mobile).
This isn't an exhaustive list of everything that touches Claude Code - it's the curated subset where I've actually read the code or notes and think the idea is worth knowing about.
Qartez MCP - codebase intelligence for AI agents
Rust MCP server that pre-indexes a codebase with PageRank, blast-radius, git co-change, and complexity signals. Agents query the graph instead of grepping files.
Codeburn - token cost TUI for Claude Code & Codex
Interactive terminal dashboard that breaks down where your AI coding tokens actually go. Surfaces the chat-vs-tool-use split most users get wrong.
agents-md - drop-in AGENTS.md template
Curated AGENTS.md preset that kills sycophancy, blocks drive-by refactors, and forces verification loops. Synthesizes Karpathy's principles with Cherny's Claude Code workflow.
abtop - htop for AI coding agents
Rust TUI that monitors Claude Code and Codex sessions: token spend, context window, rate limits, and ports in real time. Like btop but for agent runtimes.
oh-my-team - 12-agent Claude Code orchestration
Multi-agent harness for Claude Code with planning, parallel execution waves, and a five-agent review gate. Hub mode lets you drive sessions from Telegram or Slack.
AgentShield - security scanner for AI agents
CLI, GitHub Action, and GitHub App that scan agent configs, MCP servers, and tool permissions for vulnerabilities. Detects skill poisoning and prompt-injection vectors.
Open Cowork - desktop app for AI coding agents
Open-source Windows/macOS desktop that one-click installs Claude Code, MCP tools, and Skills with sandbox isolation, multi-model support, and Slack/Feishu hooks.
LLM Anonymization - pentest data scrubber
Reverse proxy for Claude Code that strips IPs, hashes, credentials, and PII before requests hit Anthropic. Dual-layer detection: local Ollama LLM plus regex.
Libretto - deterministic AI browser automations
Skill plus CLI that has coding agents generate inspectable browser-automation scripts instead of running prompts at runtime. You debug a real script, not a prompt.
agentic-stack - portable .agent folder
One memory + skills + protocols folder that plugs into Claude Code, Cursor, Windsurf, OpenCode, Hermes, or a DIY Python harness - and survives the switch.
lazyagent - terminal observability for coding agents
Watch your Claude Code, Codex, and OpenCode sessions from a tiny Go TUI. Shows what each agent is doing, no SaaS dashboard needed.
design-extract - pull a design language from any site
npx CLI plus Claude Code plugin that extracts colors, typography, spacing, and shadows from a live site into a structured design-token report.
claude-code-java - embeddable Claude Code engine
AI-agent engine for Java apps. CLI plus REST API that wraps the Claude Code execution model so you can drop it into any JVM service.
cc-telegram-bridge - Codex & Claude Code on Telegram
Multi-bot, multi-engine Telegram bridge with per-bot personality, budget caps, streaming, session resume, and an Agent Bus for parallel pipelines.
agent-flow - real-time Claude Code orchestration view
Watch your Claude Code agents think, branch, and coordinate as they run. Live visualization of subagent trees and tool calls in the browser.
agent-deck - terminal session manager for coding agents
One Bubble Tea TUI to switch between Claude, Gemini, OpenCode, Codex, and Aider sessions. Tabs, tmux feel, no electron.
parallel-code - Claude, Codex, Gemini side-by-side
Runs three coding agents in parallel git worktrees so you can compare outputs on the same task without branch swaps.
Codesight - universal AI context generator
Trims and packs codebase context for Claude Code, Cursor, Copilot, and Codex. Saves thousands of tokens per conversation by skipping vendor and generated trees.
Paseo - orchestrate coding agents from your phone
Mobile, desktop, and CLI control plane for Claude Code, Codex, Copilot, and Gemini. Kick off a task in transit and finish at the desk.
agentfiles - manage agent configs from Obsidian
Browse, create, and edit AGENTS.md, .cursor, .codex, and 13+ other agent files from inside Obsidian. Cross-tool config without leaving notes.
HolyClaude - Dockerized Claude Code workstation
Container with Claude Code, a web UI, 7 AI CLIs, a headless browser, and 50+ tools pre-wired. Useful starting point for self-hosted agent boxes.
Frequently asked
What's the difference between Claude Code orchestration and observability tools?
Orchestration tools (oh-my-team, agent-flow, paseo) coordinate multiple agents or sessions; observability tools (codeburn, abtop, lazyagent) read session state passively to surface token spend, context usage, and what agents are doing right now.
Are there security tools specifically for Claude Code?
Yes - see the agent security collection. AgentShield scans configs and MCP servers, LLM-Anonymization scrubs data before requests, and Destructive Command Guard blocks dangerous shell commands at runtime.
Which tools work across Claude Code, Codex, and other coding agents?
Most observability and orchestration tools here are multi-engine: agent-deck, codesight, paseo, parallel-code, and agentic-stack all support several coding agents in the same workflow.
Related collections
MCP servers and Model Context Protocol tools
Production MCP servers, gateways, frameworks, and clients - everything in this directory that speaks the Model Context Protocol.
Security tools for AI coding agents
Sandboxes, scanners, proxies, and governance toolkits that keep autonomous agents from doing damage.
Observability for AI coding agents
Tools that show you what your coding agents are actually doing: token spend, session state, tool calls, and parallel execution.