A

Agentsys

658 stars Marketplace

by agent-sh

AI writes code. This automates everything else · 19 plugins, 47 agents, and 39 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

agents commands hooks mcps skills

Install

1 Add the marketplace to Claude Code
/plugin marketplace add agent-sh/agentsys
2 Install any plugin from the marketplace
/plugin install <plugin-name>@agent-sh-agentsys
Or use /plugin to open the interactive plugin manager and browse the Discover tab.

Overview

Plugins
19

Plugins (19)

N

next-task

external

Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 8 specialist agents

P

prepare-delivery

external

Pre-ship quality gates: deslop, simplify, agnix, enhance, review loop, delivery validation, docs sync

G

gate-and-ship

external

Quality gates then ship - chains /prepare-delivery then /ship in one command

S

ship

external

Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback

D

deslop

external

3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)

A

audit-project

external

Multi-agent iterative code review until zero issues remain

D

drift-detect

external

Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans

E

enhance

external

Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting

S

sync-docs

external

Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes

R

repo-intel

external

Unified static analysis via agent-analyzer - git history, AST symbols, project metadata, and doc-code sync

P

perf

external

Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions

L

learn

external

Research topics online and create comprehensive learning guides with RAG-optimized indexes

A

agnix

external

Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 342 rules across 10+ AI tools

C

consult

external

Cross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control

D

debate

external

Structured multi-round debate between AI tools with proposer/challenger roles and verdict

W

web-ctl

external

Browser automation and web testing toolkit for AI agents - headless browser control, persistent sessions, auth handoff, and prompt injection defense

S

skillers

external

Learn from workflow patterns across sessions and suggest skills, hooks, and agents to automate repetitive work

O

onboard

external

Codebase onboarding - automated data collection and interactive project orientation

C

can-i-help

external

Find where to contribute to any project - matches developer skills to test gaps, stale docs, bugspots, and open issues

Highlights

19 plugins in marketplace

Web UI: https://agent-sh.github.io/agentsys/