The open agent skills ecosystem

Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line

Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.

A browser inside your terminal

Hivemind turns your traces into reusable skills across agents

AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix

Unbrowse — api native browser Skill/CLI/MCP/SDK for any agent. Auto-discovers APIs from browser traffic, generates skills on the fly to call APIs directly 100x faster, 80% cheaper locally.

Add MCP servers to your favorite coding agents with a single command.

Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

See where your AI spend goes - by task, tool, model, and project

bb app launcher for npx

Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go.

Research-first design skill for AI agents. 150K+ real app screens and flows via Refero MCP.

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Curated agent skills for CesiumJS development.

ISO 24495 Plain Language skills and plugin

Lossless context compression plugin for Claude Code & OpenCode.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

Workflow control for AI coding agents

When you can't trust yourself with your code base, trust Arbiter.