Collection · 177 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.
Claude Code Analysis - architectural reverse-engineering of the leaked source
82 docs and 15 diagrams mapping every major subsystem of Claude Code's accidentally exposed 512K-line TypeScript source - YOLO classifier, 93% context compaction, prompt-cache layout, 88+ feature flags, the custom React-Fiber terminal renderer.
trace-mcp - framework-aware codebase MCP for coding agents
MCP server with 138 tools and cross-language framework awareness (58 integrations across 81 languages). Indexes Laravel/Inertia/Vue, Rails/Hotwire, Django/HTMX edges so agents skip re-deriving call graphs. Decision memory links architectural choices to the code they're about. Local-first ONNX embeddings, optional LSP enrichment.
Garden Skills - production skill pack for Claude Code, Cursor, and Codex
Three carefully-scoped skills: web-design-engineer (with an anti-cliche blocklist that breaks the generic-AI-landing-page loop), gpt-image-2 (80+ templates, three runtime modes including advisor-only fallback), and kb-retriever (layered data_structure.md navigation for bounded local-KB retrieval). Tested across Claude Code, Claude.ai, Cursor, Codex, Gemini, OpenCode.
wanman - worktree-isolated multi-agent runtime for Claude Code and Codex
Multi-agent runtime that spawns each Claude Code or Codex agent in its own git worktree and home directory. JSON-RPC subprocess control, task pooling, artifact storage. Solves the share-a-directory failure mode that breaks most multi-agent harnesses.
PostTrainBench - can a CLI agent post-train a base LLM in 10 hours?
Benchmark measuring whether Claude Code, Codex CLI, Gemini CLI, and OpenCode can autonomously improve 4 small base models (Qwen3-1.7B/4B, SmolLM3-3B, Gemma-3-4B) on 7 evals (AIME, BFCL, GPQA, GSM8K, HealthBench, HumanEval, Arena Hard) within a single H100 GPU and 10 hours. Includes agent-as-judge anti-reward-hacking and baseline-replacement penalties for tampering.
mcptube - Karpathy-style LLM wiki for YouTube
MCP server that turns YouTube videos into a persistent, merging wiki rather than ephemeral vector chunks. Scene-change frame extraction + vision analysis captures slides, code, and diagrams that transcripts miss. 25+ MCP tools, FTS5+LLM hybrid retrieval, version history with source attribution per claim.
Claudraband - persistent, resumable Claude Code sessions over HTTP and ACP
Wraps the real Claude Code TUI with a session lifecycle layer. Resumable non-interactive workflows, HTTP daemon for remote/headless control, ACP server for editor integrations (Zed, Toad). Drives your existing Claude Code install rather than reimplementing it - keeps skills, hooks, MCPs, and approvals intact.
gpt_image_2_skill - 162-prompt gallery and skill for GPT Image 2
Curated gallery, CLI, and agentic skill for OpenAI's GPT Image 2. 162 reusable prompts across anime, gaming, photography, UI/UX, and research-figure categories. Supports text-to-image, mask-edit, multi-reference edits, and batch ops. Installable as a Claude Code plugin, Codex skill, or standalone CLI via uv.
pentest-ai-agents - Claude Code subagents for offensive security
Specialized Claude Code subagents that turn the CLI into a pentest assistant: plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.
SmolVM - one-command sandbox for Claude Code and Codex
Pre-installed sandboxed VM with Claude and Codex ready to run, plus git credentials wired up. Removes the 'press enter to accept' loop without exposing the host.
agent-of-empires - mobile-first multi-agent control plane
TUI and web UI for managing parallel Claude Code, OpenCode, Codex, Gemini, Copilot, and Factory Droid sessions. Backed by tmux and git worktrees so each agent gets its own branch.
Orca - IDE for coding agents
Stably's next-gen IDE that's built around running coding agents in parallel. First-class support for Claude Code, Codex, Cursor agent, OpenCode, Ghostty, and worktree-based orchestration.
Open Carrusel - Instagram carousels via Claude Code
Local-first Next.js app that has Claude design Instagram carousel slides and exports them as PNGs at exact platform dimensions. `/start` in Claude Code bootstraps the project.
agent-hub - one chat surface for every local and remote agent
Open-source hub that connects to Claude Code, Codex, Hermes, OpenClaw, and other agent runtimes - local or on remote machines - through a single chat UI. Less workflow-tied than Conductor.
AI Inner OS - inner-monologue plugin for AI CLIs
Cross-tool plugin for Claude Code, Codex CLI, Cursor, and OpenCode CLI that injects an optional 'inner monologue' track alongside normal output. The model decides whether and how to use it.
helix-agent - Claude Code as a personal Discord/Telegram bot
Always-on personal agent harness powered by Claude Code with Discord, Telegram, and built-in web UI front-ends. The 'phone in your pocket runs an agent' setup.
OpenTabs - API-driven browser agent
Chrome extension and MCP server that lets coding agents drive web tasks by calling site APIs instead of clicking through the DOM. Targets the brittleness of Playwright-style browser automation.
claude-remote-runner - phone remote for Claude Code
End-to-end encrypted bridge that mirrors Claude Code prompts to a mobile app, lets you approve permission requests and reply from your phone via push notifications.
agent-session-resume - cross-agent session resume skill
Skill that lets Claude Code, Codex, Antigravity, and OpenCode pick up where any of them left off by reading and writing a shared session-state file.
unclog - find and fix Claude Code context bloat
CLI that scans ~/.claude for MCPs, skills, hooks, and CLAUDE.md files, shows how many tokens each consumes before you type, and lets you remove items with reversible snapshots.
Egregore - shared memory for multiplayer Claude Code
Local MIT substrate that gives a team of Claude Code sessions a shared memory and coordination layer, spun up via npx create-egregore.
my-claude-devteam - 12-agent dev team for Claude Code
Drop-in pack of 12 specialized agents and 15 automation hooks that wires Claude Code into a structured P7/P9/P10 review and delivery workflow.
ios-simulator-skill - xcodebuild wrapper for Claude Code
Claude Code skill that wraps xcodebuild and the iOS Simulator so the agent can build, run, and interact with iOS apps without burning context on Xcode output.
asynkor - file leasing for AI agent teams
Go MCP server that gives multiple agents (or IDEs) leases on files so concurrent edits don't trample each other - a Git-free way to avoid merge conflicts in multi-agent runs.
skill-doctor - inspector for coding-agent skills
Local tool that audits installed agent skills for conflicts, precedence issues, and risk. Helps surface why a particular skill is (or isn't) firing.
pocket-ingest - voice memos to Claude Code via iCloud
iOS Shortcut records and transcribes a voice memo, drops a .txt into iCloud, and Claude Code picks it up automatically on the next session. No servers or API keys.
opencode-power-pack - 11 Claude Code skills for OpenCode
Eleven popular Claude Code skills (code-review, security-review, feature-dev, frontend-design, and more) ported to OpenCode as a single one-line plugin install.
engram - context spine for AI coding agents
Aggregates six providers (graph, git, MemPalace, Context7, Obsidian) into rich context packets that fire on every agent Read. Local SQLite, no native deps, no cloud.
codex-mcp-server - call Codex from Claude Code
MCP wrapper around the OpenAI Codex CLI that lets Claude Code (or Cursor) hand specific tasks to Codex as a sub-agent over MCP.
LeanKG - graph-backed code context
Rust knowledge-graph layer that replaces token-heavy file dumps with concise graph queries, targeting Antigravity, Claude Code, Cursor, and Gemini agents.
tnl - typed natural language plan mode
Persistent plan-mode for coding agents: agents propose a typed English contract (paths, MUST/SHOULD/MAY behaviors, non-goals), you approve, and every future session reads it before coding.
Recall - TUI search across agent session history
Local-first Rust TUI that searches Claude Code, Codex, and OpenCode session history with hybrid full-text plus semantic retrieval. Built on ratatui.
idea-reality-mcp - prior-art MCP for coding agents
MCP server that scans GitHub, Hacker News, npm, PyPI, and Product Hunt before an agent starts building, surfacing whether the idea already exists and at what scale.
claude-code-rust - native Rust port of Claude Code
Rust reimplementation of Anthropic's Claude Code CLI that avoids the upstream V8 heap OOM in long sessions. Daily-driver replacement that keeps the same UX without Node.
OpenClawdex - orchestrator UI for Claude Code and Codex
Open-source MIT UI that drives both Claude Code and Codex from one app, opens diffs in your editor instead of a side panel, and uses your existing logins instead of API keys.
AgentBox - SDK to run coding agents in any sandbox
One SDK to run Claude Code, Codex, or OpenCode inside Docker, E2B, Modal, Daytona, or Vercel sandboxes - boots each agent's native server (JSON-RPC, HTTP/SSE) instead of using non-interactive --print mode.
VTCode - Rust TUI coding agent with multi-provider support
Ratatui-based coding agent with Anthropic, OpenAI, Gemini, and Codex providers, plus local LM Studio/Ollama. Uses ast-grep for structured code search and supports MCP and Agent Client Protocol.
OpenYak - local BYOK alternative to Claude Code
MIT desktop agent for Windows/macOS/Linux with 20+ tools, MCP support, Ollama, and 100+ models via OpenRouter. No telemetry, fully local execution loop.
pydantic-deepagents - Claude Code-style agents in Python
Pydantic AI library for building deep agents with tool calling, sandboxed execution, multi-agent teams, skills, and checkpoints. Same shape as Claude Code, scriptable from Python.
mcpm.sh - MCP package manager and registry
Cross-platform CLI to search, install, and configure MCP servers across Claude Desktop, Cursor, Cline, Continue, Goose, and more. Includes router and profile features for routing requests across servers.
Graph-Hub - codebase as queryable knowledge graph
Local-first code intelligence layer that turns a codebase into a Kuzu-backed knowledge graph for Claude Code, Cursor, and other MCP clients. Reports up to 85% token savings vs grep-style retrieval.
lean-ctx - MCP context optimizer for AI coding agents
Rust MCP server plus shell hook that compresses context for Cursor, Claude Code, Copilot, Windsurf, Gemini CLI and 24 other tools. Single binary, zero telemetry.
mcp-shodan - Shodan MCP server for AI agents
MCP server exposing Shodan APIs for IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop.
soft-ue-cli - Claude Code bridge for Unreal Engine
Python CLI plus UE plugin that lets Claude Code spawn actors, edit blueprints, call functions, capture screenshots, and manage PIE sessions in real time. Uses an in-process HTTP bridge to UE5.
byob - bring your own browser to AI agents
Chrome extension and MCP bridge that lets your AI agent drive the Chrome you already have open, including authenticated sessions. Works with Claude Code and Cursor.
jeeves - TUI for browsing AI agent sessions
Terminal UI to search, preview, read, and resume Claude Code and Codex sessions in a unified view. More framework integrations planned.
revdiff - TUI diff reviewer for AI agents
Terminal diff viewer for reviewing AI-generated changes inline, annotating them, and feeding annotations back to the agent without leaving the session.
witchcraft - multi-vector semantic search in Rust
From-scratch Rust port of Stanford's XTR-Warp running on a single SQLite DB with 21ms p95 latency. Ships Pickbrain, a Claude Code/Codex skill that searches across all your past agent sessions.
claude-code-organizer - dashboard for CC configs
npx dashboard to manage Claude Code memories, configs, and MCP servers. Includes a tool-poisoning scanner, context token budget tracker, duplicate cleanup, and scope management.
maestro-orchestrate - multi-agent orchestration platform
Orchestrates Gemini CLI, Claude Code, Codex, and Qwen Code with 39 specialist subagents, parallel execution, and built-in review/debug/security/SEO/accessibility passes.
decision-linter - pre-commit judgment check
Claude Code plugin that scores 5 dimensions of a decision (Kind vs. Wicked), runs consider-the-opposite debiasing, and outputs a paste-ready memo for PRs or proposals.
coding_agent_session_search - 11-provider session search
Rust TUI and CLI that indexes and searches local coding-agent session history across Codex, Claude Code, Gemini, Cursor, Aider and seven other providers.
mex - persistent project memory for AI agents
Structured scaffold and drift-detection CLI that gives Claude Code, Cursor, and other coding agents a project-level memory file that stays in sync with the codebase.
agent-sessions - native macOS session cockpit
Swift macOS app that browses, archives, and resumes sessions across Codex CLI, Claude Code, OpenCode, Gemini CLI, Factory Droid, GitHub Copilot CLI, and OpenClaw with rate-limit tracking.
opensessions - tmux sidebar for coding agents
tmux sidebar that tracks Amp, Claude Code, Codex, and OpenCode sessions with per-thread markers, a local HTTP API, and live session state.
horizon - GPU terminal canvas for agent sessions
Rust terminal app that puts every Claude/Codex/Gemini/Kilocode session on a GPU-accelerated infinite canvas you can pan and zoom across.
sandboxed.sh - self-hosted agent sandbox orchestrator
Self-hosted Rust orchestrator that runs Claude Code and OpenCode inside isolated Linux workspaces, with skills, configs, and encrypted secrets stored in a git repo.
code-on-incus - per-agent isolated VMs with active defense
Gives each AI agent its own Incus machine with root, Docker, and systemd. Built-in detector stops threats automatically when an agent goes off-script.
sandstorm - run Claude agents in cloud sandboxes
FastAPI service for running Claude Code agents in secure E2B cloud sandboxes via API, CLI, or Slack. Single call, full agent, no infrastructure.
token-ninja - local shell command router for AI tools
MCP-fronted router that runs deterministic shell commands locally with ~19us latency, bypassing the LLM entirely. Cuts token spend on routine commands inside Claude Code, Codex, Cursor, and Copilot.
anywhere-agents - portable multi-agent config
Single config that follows you across every project and session: curated writing/routing/skills, plus a destructive-command guard for Claude Code, Codex, and friends.
ctx - cross-agent /resume for Claude Code and Codex
Local SQLite-backed skill that stores work as a persistent stream of sessions, notes, decisions, todos, and resume packs. Switch between Claude and Codex without losing the thread.
haft - engineering decisions engine with evidence decay
Go CLI that records, frames, compares, and decides engineering choices with parity enforcement and decay tracking on the underlying evidence. Integrates with Claude Code, Cursor, Gemini CLI, and Codex.
Pare - token-efficient MCP servers for dev tools
Set of structured, token-efficient MCP servers for git, test runners, npm, and Docker designed specifically for agent consumption rather than human readability.
ai-setup - sync AI configs across coding agents
CLI that continuously syncs codebase-tailored agent skills, MCP servers, and config files between Claude Code, Cursor, and Codex with one command.
codexia - agent workstation for Codex and Claude Code
Desktop workstation that adds a task scheduler, git worktree management, remote control, and skills management on top of Codex CLI and Claude Code.
entroly - self-evolving repo context compressor
Rust daemon that compresses 2M-token repos down ~95% into a Principal Engineer-style context for Cursor, Claude Code, Opus, Codex, and custom providers.
claude_agent_teams_ui - kanban for AI engineering teams
Kanban-style UI where agents take tickets, message each other, and review each other's work. Supports Codex, Claude, OpenCode, and 75+ LLM providers.
typeui - design system skills for agentic tools
Design-system skill pack that gives agentic CLIs a shared vocabulary for components, tokens, and design.md files so generated UI stays internally consistent.
MioIsland - macOS Dynamic Island for Claude Code
Swift menu-bar app that surfaces Claude Code sessions in the macOS notch: monitor progress, approve permission prompts, and jump back into a session without leaving the current window.
simulink-agentic-toolkit - Simulink MCP and skills
Official MATLAB toolkit that gives AI coding agents tools and domain knowledge for Simulink and Model-Based Design via an MCP server plus Codex/Claude Code skills.
zeroshot - autonomous engineering team CLI
JavaScript CLI that drives Claude Code, Codex, OpenCode, and Gemini CLI as a single autonomous team, taking an issue spec and returning a finished branch. Walk-away workflow with built-in orchestration.
vurb.ts - Express.js for MCP servers
TypeScript framework for building MCP servers with type-safe tools, presenters that control what the LLM sees, and built-in PII redaction. Targets Claude Code, Cursor, and other MCP clients.
hcom - cross-terminal agent messaging
Rust tool that lets AI agents in separate terminals message, watch, and spawn each other. Works with Claude Code, Gemini CLI, Codex, and OpenCode for ad-hoc multi-agent workflows.
agent-style - 21 writing rules for coding agents
Drop-in style guide for Claude Code, Codex, Copilot, Cursor, and Aider that makes their prose and commit messages read like a senior engineer instead of an LLM.
claude-historian-mcp - search past Claude Code chats
MCP server that indexes Claude Code conversation history and exposes it as a searchable tool. Lets agents recall what was decided in past sessions instead of re-deriving it.
herdr - terminal agent multiplexer
Rust agent multiplexer that lives in the terminal and lets you drive Claude Code, Codex, and other coding agents side by side in one TUI.
onWatch - real-time agent API quota tracker
Lightweight Go daemon that tracks AI API quotas across Anthropic, Codex, Copilot, Antigravity, Synthetic, and Z.ai with a Material Design 3 dashboard. Local SQLite, zero telemetry.
graymatter - persistent memory for coding agents
Go CLI that gives any AI agent persistent local memory in three lines, claiming up to 90% reduction in token use for long-running tasks. Offline-first.
mulch - growing expertise files for coding agents
Structured expertise files that live in git and accumulate over time, giving any coding agent a persistent set of project-specific lessons learned.
ai-attestation - track AI-written code in git
Open standard and git hooks that mark which lines of a repo came from an AI tool, with detectors for 19 coding agents like Claude Code, Cursor, and Copilot. CC0 spec.
skillfile - declarative skill manager for AI agents
Rust CLI that searches 110K+ community skills, installs them declaratively, and deploys them across Claude Code, Codex, Cursor, Antigravity, and friends.
chainlink - CLI issue tracker for AI agents
Rust CLI issue tracker designed for coding agents to file, claim, and close issues without a heavyweight Jira/Linear integration. Single-binary, local-first.
ccmanager - session manager for AI coding CLIs
TUI session manager that switches between Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, and Kimi CLI sessions in one place. Lets you run and supervise multiple agent runtimes from a single shell.
Palmier - phone bridge for AI coding agents
Lets you control AI agents running on your computer from your phone, and gives those agents access to phone-side capabilities (push, SMS, calendar, contacts, location). Supports 15+ agent CLIs across Linux, Windows, and macOS.
claude-code-statusline - configurable Claude Code statusline
Statusline replacement for Claude Code with real-time cost tracking, MCP server status, and themeable layouts. Bash-based and cross-platform.
claude-code-hooks - reusable Claude Code hook recipes
Growing collection of copy-paste Claude Code hooks for automation, guardrails, and lifecycle events. Each hook is documented with what it intercepts and how to customize it.
Spool - local search across agent histories
Local Electron app and CLI that searches your Claude Code sessions, Codex history, GitHub stars, and 50+ other sources with full-text search. Agents can query the same index via a tool interface.
Dispatch - background workers for Claude Code
Claude Code skill that offloads subtasks to background AI workers, freeing the main session's context window. Designed to expand effective context by parallelizing dispatched work.
oh-my-mermaid - codebase to mermaid diagrams
Claude Code skill that turns large codebases into navigable Mermaid architecture diagrams. Generates module, dependency, and call-graph views from source.
clsh - browser terminal for agent CLIs
PWA that streams a node-pty terminal to any device, letting you reach Claude Code or other agent sessions from a phone or tablet. Self-hosted with no cloud relay.
snip - LLM token-saving proxy in Go
CLI proxy for Claude Code, Cursor, Copilot, and Gemini that strips noise from LLM context with declarative YAML filters. Reports 60-90% token savings on typical agent traffic.
vibe-remote - chat-app remote for coding agents
Drives Claude Code, OpenCode, or Codex sessions from Slack, Discord, Telegram, WeChat, or Lark with real-time streaming. Useful for delegating jobs to your local agent army from anywhere.
cass-memory-system - shared memory across agents
Procedural memory layer that turns scattered Claude Code, Codex, and Cursor session transcripts into persistent, cross-agent memory. Every agent learns from every other agent's prior work.
supaconductor - parallel multi-agent orchestrator
Multi-agent orchestration system for Claude Code with parallel waves, automated quality gates, a Board of Directors review pattern, and a bundled Superpowers skill set. Ships as a Claude Code plugin.
compose-skill - Jetpack Compose agent skill
Agent skill that grounds Compose coding suggestions in actual androidx source receipts, working with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, and Windsurf. Reduces hallucinated Compose APIs.
claudetop - htop for Claude Code sessions
Real-time terminal monitor for Claude Code: cost, cache efficiency, model comparison, and alert thresholds. Targeted at users running long agent sessions who need spend visibility.
skillshare - sync agent skills across CLIs
Go CLI that syncs agent skills across Codex, Claude Code, OpenCode, and similar runtimes with one command, with team-sharing built in. Solves the per-CLI skill sprawl problem.
codemap - architectural context for LLMs
Go CLI that builds a compact project brain for AI coding agents, surfacing architecture and module relationships without dumping raw files. Plugs into Claude Code, Codex, and Cursor.
claude-bootstrap - opinionated Claude Code project init
Project initializer for Claude Code that sets up security guardrails, spec-driven structure, and AI-native conventions out of the box. Targets teams who want a consistent starting layout.
hydra - unified wrapper across AI CLIs with fallback
Go wrapper that fronts Claude Code, Codex, OpenCode, and Pi with automatic fallback and context transfer when one hits a rate limit. Keeps a coding session alive across providers.
agent-order - cross-model PRD planning workflow
Hack that has Claude and Codex independently draft PRDs for the same feature, then critique each other's plans before implementation. Avoids the anchoring bias when one model sees the other's answer first.
TokenBurner - Claude Code skill that burns tokens on demand
A deliberately wasteful Claude Code skill for stress testing, inflating metrics, or just burning budget. Useful for testing observability dashboards and rate-limit handling.
tokf - compress command output before it hits the LLM
Config-driven Rust CLI that compresses verbose command output (logs, test runs, build output) before it reaches an agent's context window. Pluggable rules for stripping noise without losing signal.
cli-continues - resume an AI session in a different tool
Cross-tool session handoff: pause work in Claude Code and pick it up in Codex, Copilot, Gemini, or Cursor with context transferred. Lets you swap agents without losing state.
agent-skills - reusable skills for Codex
Pack of reusable skills for Codex and compatible coding agents covering PRD writing, code review, and implementation review. Drop-in skill files following the skills.sh convention.
TokenTracker - cross-tool token usage dashboard
Local-first tracker for Claude Code, Codex, Cursor, Gemini, Kiro, OpenCode, and OpenClaw token usage with a web dashboard, native macOS menu bar app, and four desktop widgets. Zero-config setup.
claude-code-memory-setup - Obsidian-backed agent memory
Persistent memory pipeline for Claude Code using Obsidian and Graphify: codebase knowledge graphs plus a chat import pipeline. Author claims up to 71.5x fewer tokens per session.
claude-code-usage-bar - statusline budget readout
Real-time Claude Code statusline showing token usage, remaining budget, burn rate, and depletion time. Drop-in shell prompt addition.
figma-ui-mcp - draw and read Figma from agents
MCP server that lets Claude Code, Cursor, VS Code, and Windsurf draw UI directly on the Figma canvas via JavaScript and read existing designs back as structured data. No Figma API key required.
claude-inspector - visualize Claude Code prompt mechanics
Electron desktop app that visualizes how Claude Code constructs prompts under the hood. Useful for debugging context, tool calls, and prompt assembly when an agent goes off the rails.
repowise - codebase intelligence over MCP
Python tool exposing auto-generated docs, git analytics, dead-code detection, and architecture decision records over MCP. Designed for teams running Claude Code at scale.
claude-powerline - vim-style powerline for Claude Code
Lightweight powerline-style statusline for Claude Code with git status, session info, and color themes. TypeScript, no heavyweight dependencies.
Skills-Manager - manage skills across AI coding tools
Tauri desktop app that organizes, syncs, and shares skills across Claude Code, Codex, OpenCode, and other AI tools. React 19 frontend with a Rust core.
dagster-skills - Claude Code skills for Dagster
Curated Claude Code skill pack for working with Dagster pipelines, asset definitions, and orchestration. Drop-in /skill-name commands for data engineers.
claude-code-history-viewer - browse session history
Desktop app to browse and analyze Claude Code conversation history. Also reads opencode and Codex transcripts so you can compare runs across harnesses.
rightStage - sync AI context across terminals
Shell tool that propagates the active AI coding context across every open terminal window so a new tab knows what to work on next. Targets multi-window Claude Code and Codex flows.
claude-code-skills-zh - Chinese Claude Code skills pack
Curated collection of 100+ Claude Code skills with 18 original installable ones, organized by use case. Translations and presets for Chinese-speaking developers.
pilot-shell - production gates for Claude Code
TypeScript harness that wraps Claude Code with spec-driven plans, enforced quality gates, and persistent project knowledge. Targets teams shipping production code with the agent rather than prototyping.
awesome-autoresearch - autonomous research agent loops
Curated list of self-improvement loops, research agents, and autoresearch systems following Karpathy's framing. Useful index when designing multi-step agent harnesses.
caveman - Claude Code skill that talks like caveman
Claude Code skill that rewrites prompts in caveman speech to cut 65% of tokens with no measurable quality loss. Joke premise, real savings.
rulesync - sync agent rules across coding tools
CLI that converts and syncs project rules, skills, and MCP configs across Claude Code, Cursor, Copilot, and other AI coding agents from a single source of truth.
Claude Command Suite - slash commands for Claude Code
Library of professional slash commands for Claude Code covering code review, feature scaffolding, security audits, and architectural analysis. Drop-in workflow recipes.
paul - Plan-Apply-Unify loop for Claude Code
Structured spec-driven workflow that forces Claude Code through a Plan-Apply-Unify cycle to favor quality over raw output speed. Aimed at non-vibe coding sessions.
claude-code-skill-factory - build Claude skills at scale
Toolkit for generating production-ready Claude Skills, custom slash commands, and prompt templates from structured templates, with workflow integration helpers.
computer-agent - Rust desktop app for Claude computer use
Rust-based desktop app that lets Claude drive your terminal, browser, mouse, and keyboard via the Anthropic computer-use API. Single binary, multi-model.
claude-codex-settings - daily-driver agent config
Personal Claude Code and Codex setup with battle-tested skills, hooks, slash commands, sub-agents, and MCP servers. Useful as a starting template.
claude-code-plugins-plus-skills - plugin marketplace
Open-source marketplace with 340 plugins and 1,367 agent skills for Claude Code, plus a CCPI package manager and orchestration patterns. Bulk source for skills.
pro-workflow - self-correcting Claude Code memory
Claude Code workflow where corrections persist as compounding memory across 50+ sessions, with parallel worktrees, agent teams, and 17 prebuilt skills.
tweakcc - customize Claude Code internals
Tool to override Claude Code's system prompts, themes, spinners, input box styling, and AGENTS.md handling, plus unlock unreleased features. Works on native and npm installs.
grepai - local semantic search and call graphs
Local-first CLI that gives AI agents semantic code search and call graph traversal over your codebase using embeddings, with no cloud calls. Targets Claude Code and Cursor.
MemoMind - local GPU-accelerated memory for Claude Code
Local-first memory system for Claude Code with GPU acceleration and zero cloud dependency. Provides persistent agent memory via MCP.
vibe-check-mcp - mentor feedback for agents
MCP server that gives agents mid-task mentor feedback to break tunnel-vision, over-engineering, and reasoning lock-in. Targets long-horizon coding workflows.
OpenContext - personal context store for agents
Local context store with desktop GUI for capturing, searching, and reusing project knowledge across Codex, Claude Code, and OpenCode CLIs. Bring-your-own coding agent.
vestige - cognitive memory MCP server
Single-binary Rust MCP server that gives agents long-term memory via FSRS-6 spaced repetition, 29 cognitive modules, and a 3D dashboard. Works with Claude, Cursor, JetBrains.
claude-delegator - delegate to Codex and Gemini from Claude Code
MCP plugin that lets Claude Code delegate subtasks to Codex and Gemini directly inside a session. Useful for cross-model orchestration.
TAKT - agent coordination topology in YAML
Define multi-agent coordination, human-in-the-loop intervention points, and audit recordings in YAML, across Claude Code, Codex, and OpenCode.
claude_code_agent_farm - 20+ Claude Code agents in parallel
Orchestration framework that runs 20+ Claude Code agents concurrently with lock-based coordination, automated bug-fixing sweeps, and live tmux monitoring.
cccc - chat-style multi-agent orchestrator
Coordinates Claude Code, Codex, and Gemini CLIs as a group chat with read receipts, delivery tracking, and remote phone control. Single pip install.
claude-code-tools - utilities for CLI coding agents
Practical productivity tools for Claude Code, Codex CLI, and similar coding agents: context management, session helpers, and workflow shims.
stealth-browser-mcp - anti-bot browser automation MCP
MCP server that drives a Chrome devtools session past anti-bot systems. Lets agents write network hooks and clone UIs from natural language.
relay - hand off Claude Code session to other agents
Rust CLI that captures full Claude Code session context and hands it off to Codex, Gemini, Aider, or other agents when you hit a rate limit. Keeps work moving across providers.
memctx - autonomous session memory for Claude Code
Claude Code plugin that captures session summaries, builds searchable history, and auto-injects context into new sessions. Stops you from re-explaining the codebase every morning.
dario - use Claude Max/Pro as an API
Local proxy that exposes your Claude Max or Pro subscription as an Anthropic-compatible API. No API key, no per-token billing - just point your tools at localhost.
IDEA.md - portable idea-intent file for agents
Standard markdown format for capturing the intent of a feature so any agent (Claude Code, Codex, Gemini CLI, Copilot) can build it. Vendor-neutral counterpart to AGENTS.md.
ContextAnalyzerTerminal - per-tool-call context analyzer
Python tool that breaks down Claude Code context window usage per tool call. Surfaces which Read or Grep calls are eating the most tokens.
sp-context - persistent agent memory with BM25
Gives every agent persistent memory of team knowledge using Git plus BM25 retrieval - no vector DB, ~114 tokens per session. TypeScript/Bun, works with Claude Code.
modular-context-obsidian-plugin - Claude Code in Obsidian
Obsidian plugin that runs multiple Claude Code and Codex terminals side by side with split layouts, a skills dashboard, and session glyphs. Treats your vault as the agent control surface.
unity-cli-plugin - Claude Code/Codex plugin for Unity
Plugin that gives Claude Code and Codex 40+ commands inside Unity 2022.3+: scene editing, GameObject manipulation, profiling, and a C# REPL. Bridges agents to the Unity editor.
claude-memory-compiler - evolving codebase memory
Hooks capture Claude Code sessions, the Agent SDK extracts decisions and lessons, and an LLM compiler organizes them into cross-referenced knowledge articles. Memory that grows with the repo.
wechat-cli - query local WeChat data for LLMs
Python CLI that exposes local WeChat chat history, contacts, sessions, and favorites in a structured format agents can query. Designed as an LLM data source.
stacklit - codebase context for agents in 250 tokens
Go CLI that generates a compact codebase summary (~250 tokens) and auto-configures Claude Code, Cursor, and Aider with it. Replaces the agent's exploration phase with a single primer.
talk-normal - kill the AI slop voice
System prompt that forces any LLM to drop the corporate-overlord cadence and write like a normal person. Strips em-dashes, hedging, and 'in summary' filler.
prism - session intelligence for Claude Code
Python TUI that finds where extra tokens are burned in Claude Code sessions, why sessions fail, and what to fix. Built on Textual, focused on debugging your own usage.
google-docs-mcp - Google Docs MCP that actually works
MCP server for Google Docs that uses pattern-matching search-and-replace (like file editors) instead of character offsets, which LLMs are notoriously bad at. Fixes the broken existing options.
oh-my-agent - portable multi-agent harness
Portable harness that runs .agents-based skills, workflows, and standards across Antigravity, Claude Code, Codex, Cursor, and OpenCode. One config, every coding agent.
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.