Agentsys
658 stars Marketplaceby agent-sh
AI writes code. This automates everything else · 19 plugins, 47 agents, and 39 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
Install
/plugin marketplace add agent-sh/agentsys /plugin install <plugin-name>@agent-sh-agentsys /plugin to open the interactive plugin manager and browse the Discover tab. Overview
Plugins (19)
next-task
externalMaster workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 8 specialist agents
prepare-delivery
externalPre-ship quality gates: deslop, simplify, agnix, enhance, review loop, delivery validation, docs sync
gate-and-ship
externalQuality gates then ship - chains /prepare-delivery then /ship in one command
ship
externalComplete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback
deslop
external3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)
audit-project
externalMulti-agent iterative code review until zero issues remain
drift-detect
externalDeep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans
enhance
externalMaster enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting
sync-docs
externalStandalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes
repo-intel
externalUnified static analysis via agent-analyzer - git history, AST symbols, project metadata, and doc-code sync
perf
externalRigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions
learn
externalResearch topics online and create comprehensive learning guides with RAG-optimized indexes
agnix
externalLint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 342 rules across 10+ AI tools
consult
externalCross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control
debate
externalStructured multi-round debate between AI tools with proposer/challenger roles and verdict
web-ctl
externalBrowser automation and web testing toolkit for AI agents - headless browser control, persistent sessions, auth handoff, and prompt injection defense
skillers
externalLearn from workflow patterns across sessions and suggest skills, hooks, and agents to automate repetitive work
onboard
externalCodebase onboarding - automated data collection and interactive project orientation
can-i-help
externalFind 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/