A complete, runnable worked example of multi-agent orchestration. Four specialist agents research, write, edit, and publish a business article, with automatic delegation, machine quality gates, and an enforced human approval step. Built to be read and adapted, not used as-is.
★not rated 8 1mo agoA
tokens not measured
originalMIT
Configure a custom status line for Claude Code to display contextual information like model name, directory, and git branch at the bottom of the interface.
Orchestrate plan reviews, task generation, implementation, and code reviews in parallel across 13 coding harnesses (Codex, Cursor, opencode, pi, aider, Antigravity…) — or ask every model a free-text question about a plan.
★not rated 8 1mo agoA
tokens not measured
originalMIT
Build a source-backed GTM Brain for your company with specialist agents, skills, Grill-me questions, MVP checklists, and session handoffs. Originally built for Freckle.io's company GTM brain, then repurposed into a public plugin anyone can use.
★not rated 8 4mo agoA
tokens not measured
originalMIT
A useful plugin featuring Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development, plus custom commands and agents.
★not rated 8 7mo agoA
tokens not measured
originalMIT
Review your Claude Code collaboration across 9 dimensions in 3 categories (Communication / Engineering / Outcome) — deterministic script-computed baselines, a free-form AI diagnosis, and 5-7 playbook-driven suggestions with pastable prompts and installable assets (hooks, CLAUDE.md sections, .mcp.json). Tracks score…
A plugin for coordinating Claude and GitHub Copilot through an MCP-based development workflow. MCP is a standard way for AI tools to call external services.
★not rated 8 4mo agoA
tokens not measured
originalMIT
The open source standard for secure, private AI: operating-system enforcement is live on macOS today; Linux and Windows are not live enforcement yet, and your data stays under your own keys with current portability bounds called out in the Assurance Matrix. Wraps any MCP-compatible agent with encrypted state, approval.
★not rated 8 todayA
tokens not measured
originalApache-2.0
WebMCP agent skill for curated core coverage or route-by-route parity — inventory an existing web app, integrate approved tools, then verify and heal them in a real browser.
★not rated 8▲
+1 3d agoA
tokens not measured
originalMIT
Open-source MCP server with 500+ deterministic tools + 100 skill packs — web search, headless Chromium, PDFs, OCR, images, live data, x402 payments helpers, and 210 pure-CPU utilities. Free to self-host or pay per call in USDC on Base + 4 more chains (+ USDG on Robinhood Chain).
Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery, refactoring, copywriting, and cleaning up AI-written code and text. Every skill is a plain SKILL.md folder under the open Agent Skills standard, stack-agnostic, and ends with the check…
★not rated 8
changed todayA
tokens not measured
originalMIT
Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts.
★not rated 8▲
+3
changed todayA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: