or

<p align="center"> <img src="site/assets/logo.png" alt="AgentSys" width="120"> </p> <h1 align="center">AgentSys</h1> <p align="center"> <strong>A modular runtime and orchestration system for AI agents.</strong> </p> <p align="center"> <a href="https://www.npmjs.com/package/agentsys"><img src="https://img.shields.io/npm/v/agentsys.svg" alt="npm version"></a> <a href="https://www.npmjs.com/package/agentsys"><img src="https://img.shields.io/npm/dm/agentsys.svg" alt="npm downloads"></a> <a href="https://github.com/agent-sh/agentsys/actions/workflows/ci.yml"><img src="https://github.com/agent-sh/agentsys/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/agent-sh/agentsys/stargazers"><img src="https://img.shields.io/github/stars/agent-sh/agentsys.svg" alt="GitHub stars"></a> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> <a href="https://agent-sh.github.io/agentsys/"><img src="https://img.shields.io/badge/Website-AgentSys-blue?style=flat&logo=github" alt="Website"></a> <a href="https://github.com/hesreallyhim/awesome-claude-code"><img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code"></a> </p> <p align="center"> <b>19 plugins · 49 agents · 41 skills (across all repos) · 30k lines of lib code · 3,507 tests · 5 platforms</b><br> <em>Plugins distributed as standalone repos under <a href="https://github.com/agent-sh">agent-sh</a> org - agentsys is the marketplace &amp; installer</em> </p> <p align="center"> <a href="#commands">Commands</a> · <a href="#installation">Installation</a> · <a href="https://agent-sh.github.io/agentsys/">Website</a> · <a href="https://github.com/agent-sh/agentsys/discussions">Discussions</a> </p> <p align="center"> <b>Built for Claude Code · Codex CLI · OpenCode · Cursor · Kiro</b> </p> <p align="center"><em>New skills, agents, and integrations ship constantly. Follow for real-time updates:</em></p> <p align="center"> <a href="https://x.com/avi_fenesh"><img src="https://img.shields.io/badge/Follow-@avi__fenesh-1DA1F2?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X"></a> </p>

---

AI models can write code. That's not the hard part anymore. The hard part is everything around it - task selection, branch management, code review, artifact cleanup, CI, PR comments, deployment. AgentSys is the runtime that orchestrates agents to handle all of it - structured pipelines, gated phases, specialized agents, and persistent state that survives session boundaries.

---

Building custom skills, agents, hooks, or MCP tools? agnix is the CLI + LSP linter that catches config errors before they fail silently - real-time IDE validation, auto suggestions, auto-fix, and 399 rules for Claude Code, Codex, OpenCode, Cursor, Kiro, Copilot, Gemini CLI, Cline, Windsurf, Roo Code, Amp, and more.

What This Is

An agent orchestration system - 19 plugins, 49 agents (39 file-based + 10 role-based specialists in audit-project), and 41 skills that compose into structured pipelines for software development. Each plugin lives in its own standalone repo under the agent-sh org. agentsys is the marketplace and installer that ties them together.

Each agent has a single responsibility, a specific model assignment, and defined inputs/outputs. Pipelines enforce phase gates so agents can't skip steps. State persists across sessions so work survives interruptions.

The system runs on Claude Code, OpenCode, Codex CLI, Cursor, and Kiro. Install via the marketplace or the npm installer, and the plugins are fetched automatically from their repos.

---

The Approach

Code does code work. AI does AI work.

• Detection: regex, AST analysis, static analysis - fast, deterministic, no tokens wasted
• Judgment: LLM calls for synthesis, planning, review - where reasoning matters
• Result: 77% fewer tokens for /drift-detect vs multi-agent approaches, certainty-graded findings throughout

Certainty levels exist because not all findings are equal:

This came from testing on 1,000+ repositories.

---

Benchmarks

Structured prompts and enriched context do more for output quality than model tier. Benchmarked March 2026 on real tasks (/can-i-help and /onboard against glide-mq), measured with claude -p --output-format json. Models: Claude Opus 4 and Claude Sonnet 4.

Sonnet + AgentSys vs raw Opus

Same task, same repo, same prompt ("I want to improve docs"):

Sonnet + agentsys produced more output with higher specificity than raw Opus - at 40% lower cost.

With agentsys, model tier matters less

Once the pipeline provides structured prompts, enriched repo-intel data, and phase-gated workflows, the model does less heavy lifting. The gap between Sonnet and Opus narrows:

Both models reached the same outcome quality - Sonnet just costs less to get there. The structured pipeline captures most of the gains that would otherwise require a more expensive model.

What this means

The investment shifts from model spend to pipeline design. Better prompts, richer context, enforced phases - these compound in ways that model upgrades alone don't.

---

Commands

Each command works standalone. Together, they compose into end-to-end pipelines.

---

Skills

41 skills included across the plugins:

External skill plugins (standalone repos, installed separately):

Skills are the reusable implementation units. Agents invoke skills; commands orchestrate agents. When you install a plugin, its skills become available to all agents in that session.

---

Quick Navigation

---

Skill-Only Plugins

Plugins that provide skills without a / command. Installed alongside agentsys; skills become available to all agents.

glide-mq

Build message queues, background jobs, and workflow orchestration with glide-mq - high-performance Node.js queue on Valkey/Redis.

Key features: per-key ordering, group concurrency, runtime group rate limiting (job.rateLimitGroup()), token bucket, DAG workflows, broadcast pub/sub, step jobs, deduplication, serverless producers.

Skill plugin → | glide-mq docs → | npm →

---

Command Details

/next-task

Purpose: Complete task-to-production automation.

What happens when you run it:

1. Policy Selection - Choose task source (GitHub Issues, GitHub Projects, GitLab, local file), priority filter, stopping point
2. Task Discovery - Shows top 5 prioritized tasks, you pick one
3. Worktree Setup - Creates isolated branch and working directory
4. Exploration - Deep codebase analysis to understand context
5. Planning - Designs implementation approach
6. User Approval - You review and approve the plan (last human interaction)
7. Implementation - Executes the plan
8. Pre-Review - Runs deslop-agent and prepare-delivery:test-coverage-checker
9. Review Loop - Multi-agent review iterates until clean
10. Delivery Validation - Verifies tests pass, build passes, requirements met
11. Docs Update - Updates CHANGELOG and related documentation
12. Ship - Creates PR, monitors CI, addresses comments, merges

Phase 9 uses the orchestrate-review skill to spawn parallel reviewers (code quality, security, performance, test coverage) plus conditional specialists.

Agents involved:

Cross-plugin agent:

Usage:

/next-task              # Start new workflow
/next-task --resume     # Resume interrupted workflow
/next-task --status     # Check current state
/next-task --abort      # Cancel and cleanup

Full workflow documentation →

---

/prepare-delivery

Purpose: Run all pre-ship quality gates without shipping. Use after completing implementation manually or outside /next-task.

What it runs (in order):

1. Pre-review gates (parallel) - deslop + /simplify + prepare-delivery:test-coverage-checker
2. Config lint (conditional) - agnix + /enhance when changes touch agent/skill/plugin files
3. Review loop - 4 core reviewers + conditional specialists, max 5 iterations
4. Delivery validation - tests pass, build passes, requirements met
5. Docs sync - sync-docs agent updates documentation

/prepare-delivery                    # Run all quality gates
/prepare-delivery --skip-review      # Skip review loop
/prepare-delivery --skip-docs        # Skip docs sync
/prepare-delivery --base=develop     # Against a specific base branch

Does NOT create PRs or push - use /ship or /gate-and-ship after.

---

/gate-and-ship

Purpose: Quality gates then ship in one command. Chains /prepare-delivery then /ship.

/gate-and-ship                       # Full: quality gates + ship
/gate-and-ship --skip-review         # Skip review, still ship
/ga