Daily Digest — May 4, 2026

obra/superpowers

178K stars (up from 159.3K on April 26) — Jesse Vincent's structured development methodology for Claude Code and 13+ other agents. Five composable phases: Brainstorm, Design (interactive HTML mockups), Plan (git-worktree task breakdown), Code (parallel subagents with 6-category self-check), and Verify (security audit). Official Anthropic marketplace plugin since January. v5.0.7 current.

copy/plugin install superpowers@claude-plugins-official

gstack (garrytan)

82.7K stars (12K forks). Garry Tan's open-sourced Claude Code setup — 23 specialist skills as slash commands: CEO, Designer, Eng Manager, QA Lead, Security Officer, Release Engineer, and more. Surpassed 10K stars in its first 48 hours. The design-review skill catches AI slop before it ships, making it the most-watched anti-slop harness in the ecosystem right now.

copySee README

CC Switch (farion1231)

58.4K stars for a Tauri-powered desktop app that unifies Claude Code, Codex, OpenCode, OpenClaw, and Gemini CLI in one GUI — 50+ provider presets, one-click MCP and Skills sync across all agents, and a system-tray switcher. Become the go-to desktop control panel for teams running multiple AI CLI tools side-by-side.

copybrew tap farion1231/ccswitch && brew install --cask cc-switch

get-shit-done (gsd-build)

59.6K stars. v1.40.0 shipped May 3 with per-phase model routing, dynamic failure-tier escalation, and a --research-phase flag for the plan command. The --minimal install profile cuts cold-start system-prompt overhead by 94% (from ~12K tokens to ~700), making it the single biggest token win per install in the ecosystem.

copynpx get-shit-done-cc@latest

caveman (JuliusBrussee)

52.9K stars. v1.7.0 landed May 1 adding cavecrew (multi-agent cave team), stats receipts, and MCP-shrink — a new MCP input-token compressor that cuts ~46% of input tokens every session on top of the existing 65% output-token reduction. One of the most-installed cost skills in the ecosystem.

copycurl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash

oh-my-openagent / OMO (code-yeongyu)

55K stars. Multi-model orchestration harness that transforms a single AI coding assistant into 11 parallel specialists (Sisyphus orchestrator on Claude Opus 4.7, sub-agents on Gemini/Kimi/GLM). Ships 52 lifecycle hooks, 26 tools, and a 3-tier MCP system — each task auto-routes to the cheapest capable model, making it the most cost-aware harness after caveman.

Skyvern (Skyvern-AI)

21.5K stars, v1.0.32 shipped May 1. AI-powered browser automation that gives Claude Code eyes and hands in any web UI — acts, extracts, validates, handles 2FA, integrates with password managers (Bitwarden, 1Password, LastPass). `skyvern setup claude-code` wires it directly into Claude Code; Anthropic Claude is a first-class supported LLM. Cuts the gap between code-generation and real-world web workflows.

copypip install skyvern && skyvern setup claude-code

Claude for Financial Services (Anthropic)

Official Anthropic plugin suite with 7.9K stars: 41 skills, 38 commands, and 11 MCP integrations covering investment banking (CIMs, merger models), equity research, private equity (IC memos, diligence), and wealth management. Real-time data connectors for S&P Global, Daloopa, Morningstar, FactSet, LSEG, PitchBook, and Moody's. Slash commands: /comps, /dcf, /earnings, /ic-memo. Partner-built plugins from LSEG and S&P Global included.

copyclaude plugin marketplace add anthropics/financial-services-plugins && claude plugin install financial-analysis@financial-services-plugins

Hermes Agent (NousResearch)

131K GitHub stars in ten weeks — faster than LangChain or AutoGPT. NousResearch's self-improving agent creates skills from experience, searches past conversations, and builds persistent user models across sessions. v0.12.0 shipped April 30. Runs Claude via OpenRouter or direct API; includes a Claude Code SKILL.md in the repo.

copycurl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

everything-claude-code (affaan-m)

173K stars and v2.0.0-rc.1 released in April with desktop dashboard GUI, operator workflows, media tooling, and a Rust-based ECC 2.0 alpha control plane. Bundles 48 agents, 182 skills, 68 command shims, and multi-language rules — the highest-starred Claude Code harness on GitHub.

copy/plugin marketplace add https://github.com/affaan-m/everything-claude-code

claude-mem (thedotmack)

71.4K stars and v12.3.8 with 244 releases. Hooks into Claude Code's session lifecycle, compresses tool usage into semantic summaries via the Agent SDK, and stores them in a local SQLite+Chroma vector DB — injecting relevant context automatically on next session start. @simonscrapes compared all Claude memory systems this week and claude-mem topped for zero-config simplicity.

copynpx claude-mem install

OpenClaude (Gitlawb)

25.8K stars. Open-source coding-agent CLI derived from the Claude Code codebase, reengineered for multi-provider use — OpenAI, Gemini, GitHub Models, Ollama, and local servers all work with saved profiles via /provider. Supports bash, file ops, grep, glob, agents, tasks, MCP, slash commands, streaming, vision, and VS Code extension integration. MIT licensed, not affiliated with Anthropic.

copynpm install -g @gitlawb/openclaude

career-ops (santifer)

42.1K stars for an AI-powered job search system built entirely on Claude Code: 14 skill modes, a Go terminal dashboard, PDF resume generation, and Playwright-powered batch scanning of 45+ career portals. The creator used it to evaluate 740 job listings and land a Head of Applied AI role — one of the most concrete real-world Claude Code skill systems to ship this year.

copygit clone https://github.com/santifer/career-ops.git && cd career-ops && npm install && npx playwright install chromium

nanobot (HKUDS)

41.6K stars. Ultra-lightweight personal AI agent at v0.1.5.post3 (April 29). Keeps the core agent loop small and readable while supporting MCP, multi-platform chat (Telegram, Discord, Slack, WeChat), 24/7 market analysis, and full-stack software engineering tasks. Built as an open alternative to Claude Code's architecture — inspects Claude Code's design philosophy but runs any LLM.

copypip install nanobot-ai

awesome-claude-code-subagents (VoltAgent)

19.1K stars. 131+ specialized Claude Code subagent definitions organized across 10 categories — language specialists, infrastructure, QA, data/AI, DevEx, business/product, meta-orchestration, and research/analysis. Each subagent runs in an isolated context window, carries domain-specific instructions, has granular tool permissions, and includes a model field that auto-routes to the right Claude tier. Copy any .md file into .claude/agents/ to activate.

copySee README (copy .md files into .claude/agents/)