Agent Toolkit — August 23, 2026

27 things to install into your agent this week: skills, commands, servers, and plugins, roughly half of them proven defaults and half of them barely a month old.

🧠 Skills & Capability Packs

anthropics/skills

Anthropic's own skill collection is the reference implementation of the Agent Skills spec: document creation for docx, pdf, pptx, and xlsx, Playwright-based webapp testing, and a skill that writes new MCP servers for you. Add it with /plugin marketplace add anthropics/skills, then /plugin install document-skills@anthropic-agent-skills (swap in example-skills for the other set). With 171k stars and commits landing this week, it's the version everyone else's skill pack gets measured against. Pricing: free, open source.

obra/superpowers

Superpowers turns a set of coding habits into skills that fire automatically mid-session: brainstorming before building, TDD's red-green-refactor, systematic debugging, working in git worktrees. Install with /plugin marketplace add obra/superpowers-marketplace then /plugin install superpowers@superpowers-marketplace. Version 6.3.0 shipped August 12 with Devin CLI and Hermes Agent support, and at 276k stars it's become close to a shared methodology for this ecosystem. Pricing: free, open source.

Vincentwei1021/video-shotcraft

Five weeks old and already past 6,000 stars: video-shotcraft hands Claude Code or Codex a library of 152 cinematic shot recipes and 200 motion previews so it can cut a beat-synced promo video in Remotion instead of guessing at camera language. Clone the repo and symlink it into ~/.claude/skills/video-shotcraft. Commits have landed almost daily since it launched on July 19, 2026. Pricing: free, open source.

🗂️ Slash Commands & Prompt Packs

wshobson/agents

This plugin marketplace packages 105 slash commands with 202 agents and 181 skills, each written natively for its harness rather than as a lowest-common-denominator prompt, so the same install works across Claude Code, Cursor, Codex CLI, OpenCode, and Copilot. Run /plugin marketplace add wshobson/agents then /plugin install <name> for whichever set you need. It's pushed commits every day this week and sits at 39k stars, which makes it the default starting point for a command library. Pricing: free, open source.

hesreallyhim/awesome-claude-code

Check whether someone already wrote your slash command before you write your own: this is the list most Claude Code command recommendations trace back to, with a dedicated section linking straight to ready-to-drop .md files. Grab one and put it in .claude/commands/. At 52.9k stars and updated almost daily, it's the reference index rather than a random link dump. Pricing: free, open source.

ccplugins/awesome-claude-code-plugins

Most "awesome" lists just point elsewhere; this one hosts working plugins directly, among them commit-commands, pr-review-toolkit, feature-dev, and security-guidance, plus an index of third-party marketplaces. A backlog of pending submissions got cleared and merged on August 12, 2026, which is why the list is noticeably fuller than it was a month ago. Install with claude plugin marketplace add ccplugins/awesome-claude-code-plugins. Pricing: free, open source.

🔌 MCP Servers & Connectors

modelcontextprotocol/servers

The official MCP servers repo bundles filesystem access, git operations, web fetch, a memory knowledge graph, and sequential thinking, and most MCP clients ship it as their example config. Add a server with npx -y @modelcontextprotocol/server-memory for the TypeScript ones or uvx mcp-server-git for the Python ones. Closing in on 90k stars, it's still the place to start if you're not sure where MCP begins. Pricing: free, open source.

microsoft/playwright-mcp

Playwright-mcp gives an agent real browser control, clicking, filling forms, navigating, reading page state, through the accessibility tree instead of screenshots, so no vision model is required. The whole setup is one entry in mcp.json pointing at npx @playwright/mcp@latest. Microsoft maintains it directly, and at 36k stars it's the browser-automation server most people reach for first. Pricing: free, open source.

github/github-mcp-server

GitHub's own MCP connector for issues, PRs, code search, and reviews has been on close to a weekly release cadence: v1.7.0 in July moved it onto the new MCP spec's stateless sessions, v1.9.0 turned on semantic search by default, and v1.10.1 landed August 20, 2026. Point an mcp.json entry at the binary or Docker image from the README. It's already the default GitHub connector at 32.5k stars, but the release pace is the real reason to check in on it this month. Pricing: free, open source.

🧩 Plugins & IDE Extensions

Claude Code for VS Code

Anthropic's official VS Code extension puts Claude Code inside the editor: inline diff review, @-mentions tied to your current selection, autonomous file edits and terminal runs, and a checkpoint system to roll back what it did. Install it from the VS Code Marketplace like any other extension. It's at 23.8 million installs with a version bump on August 18, 2026, which says something about how fast this one still moves at that size. Pricing: free extension, requires a paid Claude plan or API account.

Cline

Cline is the open-source alternative that asks for your approval before every file edit, terminal command, or browser action, which makes it the pick for anyone who wants an autonomous agent they can still watch closely. It's bring-your-own-model, so point it at whichever provider you already pay for. Five million installs and an Apache 2.0 license make it the default open-source agent for VS Code. Pricing: free, open source, bring your own API key.

Claudian

Claudian drops Claude Code, Codex, Grok, Opencode, and Pi into an Obsidian vault as agents that can read, search, and edit vault files directly, turning the vault itself into the agent's working directory. Install it from Community Plugins by searching "Claudian." It shipped v2.2.4 days before this digest went out and has already crossed 1.8 million downloads, unusually fast growth for a plugin this specific. Pricing: free, open source, bring your own agent CLI or API key.

Junie by JetBrains

Junie is JetBrains's own agentic coding tool for the IntelliJ family, IntelliJ IDEA, PyCharm, WebStorm, and it left beta for general availability in June 2026 with IDE-native context and an allowlist for terminal, build, and MCP actions. Install it from the JetBrains Marketplace like any other plugin. Bundled into the AI Pro and Ultimate subscription tiers, it's JetBrains's answer to what Claude Code and Cursor already do inside VS Code. Pricing: freemium, bundled with JetBrains AI Pro ($10/mo) or Ultimate ($30/mo).

🔁 Agent Loops & Harnesses

Ruflo (formerly Claude-Flow)

Claude-Flow renamed itself Ruflo this year and kept doing what made it popular: hierarchical swarm orchestration for Claude Code, with consensus-based coordination and vector memory that lets agents recall what worked in past sessions. Run npx ruflo@latest init wizard, or register it directly as an MCP server. Nearly 70k stars and daily point releases through this week keep it the default pick once a single agent isn't enough. Pricing: free, open source; a hosted web UI is a separate paid add-on.

ralphex

Ralphex runs Claude Code or Codex through a five-phase review loop per task: a fresh session, a parallel first review by five agents, an optional external Codex pass, a focused second review, then finalize, so each task gets checked before it's called done instead of trusting one long-running session. Install with go install github.com/umputun/ralphex/cmd/ralphex@latest or brew install umputun/apps/ralphex. Version 1.6.0 shipped June 26, 2026 with Fable model support and a web dashboard, and commits are still landing this week. Pricing: free, open source.

gh-aw (GitHub Agentic Workflows)

GitHub's own agentic-workflows project lets you define automations in Markdown and YAML that compile into GitHub Actions, splitting a read-only sandboxed agent job from a separately scoped job that applies the writes it produced. It's been in public preview since June 11, 2026 and already has 5,000 stars. Install it with gh extension install github/gh-aw. Pricing: free, uses your own Actions minutes and model API costs.

⌨️ CLI Agents & Runners

Claude Squad

Claude Squad runs several terminal agents, Claude Code, Codex, Aider, Gemini, OpenCode, Amp, side by side, each in its own git worktree and tmux session, with a TUI for reviewing diffs across all of them at once. Install with the one-line curl script or brew install claude-squad. It's at 8.4k stars with a commit as recent as August 20, 2026, and it's usually the first name that comes up when parallel agent sessions get mentioned. Pricing: free, open source.

CLI Agent Orchestrator (CAO)

AWS Labs built this to coordinate Claude Code, Codex, and Kiro as specialist workers under a supervisor agent, each isolated in its own tmux session so one agent's context doesn't bleed into another's. Run uv tool install git+https://github.com/awslabs/cli-agent-orchestrator.git@main --upgrade, or grab it from PyPI. It's shipping fast: v2.4.1 landed August 4, 2026, with commits nearly every day since. Pricing: free, open source.

Parallel Code

Parallel Code, from the developer behind Super Productivity, is a desktop app that fires off Claude Code, Codex, and Gemini on the same task in separate git worktrees, then lets you diff the results side by side and merge or discard each one. Download the DMG, AppImage, or .deb from the releases page, or build it from source. It's under 1,000 stars, but daily commits through August 21, 2026 make it early rather than untested. Pricing: free, open source.

🛡️ Rules, Hooks & Guardrails

AGENTS.md standard

AGENTS.md is the format itself: one file in your repo root that over 30 coding agents, Claude Code, Cursor, Codex, Copilot among them, already read for project rules and context, so writing it once covers whichever agent a teammate happens to be running. There's nothing to install beyond the file. With nearly 24k stars and adoption across more than 60,000 repos, it's the closest thing this space has to a shared convention. Pricing: free, open standard.

cc-safety-net

cc-safety-net is a PreToolUse hook that catches destructive commands, rm -rf, force pushes, dd, mkfs, and reads of secrets like SSH keys or .env files before they execute, including ones buried inside shell wrappers or one-liners. Run npx -y cc-safety-net@latest install and it's wired in. The v2 line added support for a dozen agents beyond Claude Code and is shipping near-daily point releases, most recently August 23, 2026. Pricing: free, open source.

claude-code-hooks

This is a marketplace of about twenty installable hook plugins, blocking dangerous commands, protecting secrets, enforcing git safety, tracking context cost, each running as an out-of-process guard so a prompt injection inside the conversation can't disable it. Install the marketplace with /plugin marketplace add karanb192/claude-code-hooks, then /plugin install <hook-name>@claude-code-hooks. It's a smaller project, under 500 stars, but commits landed the same week as this digest. Pricing: free, open source.

💾 Memory & Context

MCP Memory Service

MCP Memory Service gives an agent persistent memory across sessions, backed by local ONNX embeddings and a knowledge graph, with a REST API that also plugs into LangGraph, CrewAI, and AutoGen pipelines outside of Claude entirely. Run pip install mcp-memory-service, then point your MCP config at it. It's been running since December 2024, and v11.8.2 shipped the same day this digest was written, so it's actively maintained rather than coasting. Pricing: free, open source; optional paid Cloudflare sync.

Context Mode

Context Mode sandboxes noisy tool output before it reaches the model's context window, the project claims a 98% size reduction, and persists session state in SQLite so a compaction event doesn't erase what the agent already knew. It works across 17 coding-agent platforms through hooks; npm install -g context-mode plus one config line is the whole install. It crossed 20k stars fast after launching in February 2026, and the core stays free while a hosted cost-analytics dashboard is the paid layer. Pricing: free core, optional paid "Insight" cloud dashboard.

mcp-memory

Ten days old at the time of writing and already at 193 stars: mcp-memory stores an agent's memories as plain Markdown files in an OKF-like format, then indexes them in SQLite FTS5 for search that returns in under 20 milliseconds. Clone the repo, run python3 setup.py, then register it as an MCP server. It's a smaller, more legible alternative to memory servers that hide everything behind a database file you can't read. Pricing: free, open source.

🧰 Workflow Recipes & Templates

claude-code-templates

claude-code-templates is a browsable, installable library of ready-made agents, slash commands, hooks, and MCP configs. Running npx claude-code-templates@latest opens an interactive picker so you install exactly the bundle you need instead of copying files by hand. At 30.4k stars and commits landing today, it's usually the fastest way from an empty .claude/ folder to a working setup. Pricing: free, open source.

maestro-flow

Maestro-flow's predecessor, the older Claude-Code-Workflow repo, was archived in June with a migration notice pointing here; the new version adds a knowledge graph so the planning, execution, and validation agents it wires together learn from past runs instead of starting cold each time. Run npm install -g maestro-flow then maestro install to get it working across Claude Code, Codex, and Gemini. Version 0.5.80, adding Arch-KB search templates, shipped the same day as this digest. Pricing: free, open source.

---

27 tools this week. Found a dead link or have something to add? Reply to the email.