3,224 tagged ai-agents, measured the same way as everything else here.
Browse within: agentic-ai 241claude-code-plugin 218LLM 185cursor 178cli 147agents 128agents-md 108prompt-engineering 108Science 99ai-coding 74agentic-coding 65ai-tools 63skills 60agentskills 53
Plugin Claude Code
Bundles 1 skill · 94 tokens together
Background QA for macOS apps via the offstage harness: AX perception, semantic port actuation, canonical pixel goldens, ground-truth verification.
Plugin Claude Code
Bundles 1 skill, 7 MCP servers · 237 tokens together
Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Bun.serve + bun:sqlite + React 19 + Astryx workbenches with a two-way human↔agent loop over SSE — eval viewers, PR review rooms, document-redline surfaces, grid/spreadsheet editors, multi-surface triage queues, and trace replays…
Plugin Claude Code
Plugin marketplace listing 1 plugin: founder-os.
Plugin Claude Code
Bundles 4 skills, 8 hooks · 226 tokens together
A plugin for coding agents. They ship secure code. Steers the write and can ask or deny before a file is saved.
Plugin Claude Code
Bundles 1 skill · 89 tokens together
Concise, plain-language response mode for readers with a limited attention span and/or smaller vocabulary. Cuts filler, hedging, and politeness. Keeps every fact. Caps answer options at 3 with a read-more escape hatch. 150 words / 45 sec by default; /junebug lite doubles the budget.
Plugin Claude Code
Bundles 40 skills, 17 commands, 44 agents, 9 hooks · 3,036 tokens together
Turn Claude Code into a structured development partner — session lifecycle, named code reviewers, research pipelines, and 35+ workflow skills that enforce quality from plan through execution.
Plugin Claude Code
Bundles 8 skills, 1 agent, 3 hooks · 710 tokens together
Quality-first harness for autonomous AI coding agents: deterministic gates + a default-FAIL evaluator in the close path of the loop, over a Beads task spine. Done is earned, not asserted. Unifies GSD + Beads; stack-agnostic.
EvilFreelancer/screenshotting-gui
Plugin Claude Code
Bundles 1 skill · 170 tokens together
Capture clean, repeatable screenshots of a GUI desktop app (Cursor, IDEs, browsers) on an isolated Xvfb display: drive it with python-Xlib (XTEST), capture with ImageMagick, annotate with a highlight box, crop or arrow. For docs, courses and bug reports; never touches the operator's live :0 desktop.
Plugin Claude Code
Bundles 3 skills, 7 commands, 1 MCP server · 285 tokens together
A disciplined control loop for multi-window Claude Code work: a controller window dispatches scoped task packages across a tmux-resident fleet, collects immutable target results, obtains independent Test validation, reviews the evidence, and decides the next step. Explicit on-disk state roots keep the run auditable…
Plugin Claude Code
Bundles 5 skills, 9 commands, 1 agent, 3 hooks · 759 tokens together
Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud.
Plugin Claude Code
Bundles 8 skills, 4 agents, 2 MCP servers · 839 tokens together
Structured AI-assisted development workflow: plan, critique, implement, review, QA — with deterministic pre-push enforcement below the LLM layer.
Plugin Claude Code
Claude Peek channel — send and receive messages via the notch UI.
Plugin Claude Code
Bundles 8 skills, 2 commands · 631 tokens together
The complete ArchAgent workflow plugin: install and authenticate the public ArchAgent CLI, then author agents, build scripts and workflows, manage configs, chat with running agents, and embed agents from Claude Code.
Plugin Claude Code
Bundles 16 skills · 1,892 tokens together
End-to-end development skills for Claude Code: framework-specific expertise for frontend (React, Vue), backend (NestJS, FastAPI), mobile (Flutter, React Native), infra (Terraform), and QA (Playwright E2E, Appium real-device testing). Every skill enforces verification loops - type-check until clean, tests pass, change…
Plugin Claude Code
Bundles 1 skill · 89 tokens together
Talk to the Claude agent in another domux worktree: address a peer by name to send it a message and read its output (domux send/read/peek).
Plugin Claude Code
Bundles 1 agent · 71 tokens together
Subagent for deep architectural analysis of WordPress plugins with persistent memory. Depends on the wp-mnemon skill from the wp-skills marketplace.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 11 tokens together
MCP server that orchestrates multiple Claude CLI instances as parallel workers with a real-time dashboard.
Plugin Claude Code
Bundles 1 skill · 81 tokens together
Premium, keynote-style UI skill for coding agents — dark, minimal, cinematic reveals with disciplined motion.
Plugin Claude Code
Bundles 2 commands, 1 hook, 1 MCP server · 16 tokens together
Local-first Context7 alternative — indexes JS/TS dependency docs with a 4-stage RAG pipeline (vector + BM25 + RRF + cross-encoder reranking). Uses TEI Docker containers for GPU-accelerated embeddings and reranking.
Plugin Claude Code
Bundles 1 skill · 29 tokens together
Prove a new test fails against the old code before trusting green.
Plugin Claude Code
Kernel-grade persistent memory for Claude Code. Remembers decisions, constraints, and context across sessions — designed like an OS memory subsystem, not a database.
Plugin Claude Code
Bundles 1 skill · 127 tokens together
Anti-cramped spacing skill for AI-generated UI — three dials, one spacing scale, vertical rhythm, optical alignment, accessibility floors, and density discipline.
Plugin Claude Code
Bundles 4 skills, 1 hook · 159 tokens together
Focused SpecGate skills for project setup, work preparation, and delivery.
Plugin Claude Code
Bundles 1 skill · 53 tokens together
Compile a single AI supagent into multiple AI subagents.