agent-sh/agentsys

AgentSys is a modular runtime and orchestration system for AI agents, providing skill installation, versioning, and execution as lightweight containerized modules across multiple AI coding assistants.

productivity

🔌perf🔌Plugin

A 10-phase structured performance investigation skill with baselines, profiling, hypothesis testing, and evidence-backed optimization decisions, part of the AgentSys orchestration system.

development

🔌gate-and-ship🔌Plugin

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

productivity

🔌ship🔌Plugin

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

deployment

🔌audit-project🔌Plugin

Multi-agent iterative code review until zero issues remain

development

🔌enhance🔌Plugin

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

development

🔌sync-docs🔌Plugin

Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes

development

🔌learn🔌Plugin

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

productivity

🔌consult🔌Plugin

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

productivity

🔌skillers🔌Plugin

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

productivity

🔌agnix🔌Plugin

Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 385 rules across 10+ AI tools

development

🔌debate🔌Plugin

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

productivity

🔌web-ctl🔌Plugin

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

automation

🔌prepare-delivery🔌Plugin

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

productivity

🔌deslop🔌Plugin

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

development

🔌can-i-help🔌Plugin

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

productivity

🔌repo-intel🔌Plugin

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

development

🔌onboard🔌Plugin

Codebase onboarding - automated data collection and interactive project orientation

productivity

🔌drift-detect🔌Plugin

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

productivity

🏪Marketplaces1

🏪agent-sh-agentsys🏪Marketplace

AgentSys is a modular runtime and marketplace for orchestrating AI-agent pipelines across Claude Code, Codex CLI, OpenCode, Cursor, and Kiro — bundling 19 plugins, 47 agents, 40 skills, and 3,583 tests in ~30k lines of library code. Each plugin is a standalone repo under the agent-sh org, with phase-gated pipelines, certainty-graded findings (HIGH/MEDIUM/LOW), and deterministic code-based detection separated from LLM-based judgment.

plugins:19productivitydeployment

Back to Home