AgentSys

A modular runtime and orchestration system for AI agents.

24 plugins · 49 agents · 44 skills (across all repos) · 30k lines of lib code · 3,518 tests · 5 platforms

Plugins distributed as standalone repos under agent-sh org - agentsys is the marketplace & installer

Commands · Installation · Website · Discussions

Built for Claude Code · Codex CLI · OpenCode · Cursor · Kiro

New skills, agents, and integrations ship constantly. Follow for real-time updates:

---

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 423 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 - 24 plugins, 49 agents (39 file-based + 10 role-based specialists in audit-project), and 44 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:

Level	Meaning	Action
HIGH	Definitely a problem	Safe to auto-fix
MEDIUM	Probably a problem	Needs context
LOW	Might be a problem	Needs human judgment

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"):

Configuration	Cost	Output tokens	Result quality
Opus, no agentsys	$1.10	2,841	Generic recommendations, no project-specific context
Opus + agentsys	$1.95	5,879	Specific recommendations with effort estimates, convention awareness, breaking change detection
Sonnet + agentsys	$0.66	6,084	Comparable to Opus + agentsys: specific, actionable, project-aware

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:

Plugin	Opus	Sonnet	Savings
/onboard	$1.10	$0.30	73%
/can-i-help	$1.34	$0.23	83%

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

Scenario	Model cost	Quality
Without agentsys	Need Opus for good results	Depends on model capability
With agentsys	Sonnet is sufficient	Pipeline handles the structure, model handles judgment

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

Command	What it does
/next-task	Task workflow: discovery, implementation, PR, merge
/prepare-delivery	Pre-ship quality gates: deslop, review, validation, docs sync
/gate-and-ship	Quality gates then ship (/prepare-delivery + /ship)
/banthis	Durable negative memory: persist banned agent behaviors
/agnix	Lint agent configurations (423 rules)
/ship	PR creation, CI monitoring, merge
/deslop	Clean AI slop patterns
/perf	Performance investigation with baselines and profiling
/drift-detect	Compare plan vs implementation
/audit-project	Multi-agent iterative code review
/enhance	Plugin, agent, and prompt analyzers
/repo-intel	Unified static analysis - git history, AST symbols, project metadata
/sync-docs	Sync documentation with code changes
/learn	Research topics, create learning guides
/consult	Cross-tool AI consultation
/debate	Structured debate between AI tools
/release	Versioned release with ecosystem detection
/skillers	Workflow pattern learning and automation
/skill-curator	Create and improve reliable SKILL.md files
/system-prompt-curator	Create and improve autonomous agent system prompts
/onboard	Codebase orientation for newcomers
/can-i-help	Match contributor skills to project needs

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

---

Skills

44 skills included across the plugins:

Category	Skills
Workflow	discover-tasks, prepare-delivery, check-test-coverage, orchestrate-review, validate-delivery
Message Queues	glide-mq-migrate-bee, glide-mq-migrate-bullmq, glide-mq
Enhancement	enhance-agent-prompts, enhance-claude-memory, enhance-cross-file, enhance-docs, enhance-hooks, enhance-orchestrator, enhance-plugins, enhance-prompts, enhance-skills, skill-curator, system-prompt-curator
Performance	baseline, benchmark, code-paths, investigation-logger, perf-analyzer, profile, theory-gatherer, theory-tester
Cleanup	deslop, sync-docs
Code Review	audit-project
AI Collaboration	consult, debate, learn, recommend, skillers-compact
Onboarding	can-i-help, onboard
Release	release
Analysis	drift-analysis, repo-intel
Memory	banthis
Linting	agnix

External skill plugins (standalone repos, installed separately):

Category	Skills	Plugin
Message Queues	glide-mq, glide-mq-migrate-bullmq, glide-mq-migrate-bee	agent-sh/glidemq
Languages	mojo	agent-sh/mojo
Languages	ada-spark	agent-sh/ada-spark

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

Section	What's there
The Approach	Why it's built this way
Benchmarks	Sonnet + agentsys vs raw Opus
Commands	All 24 commands overview
Skills	44 skills across plugins
Skill-Only Plugins	glide-mq and other non-command plugins
Command Details	Deep dive into each command
How Commands Work Together	Standalone vs integrated
Design Philosophy	The thinking behind the architecture
Installation	Get started
Research & Testing	What went into building this
Documentation	Links to detailed docs

---

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.

Skill	What it does
glide-mq	Greenfield queue development - queues, workers, ordering, rate limiting, flows, broadcast, step jobs
glide-mq-migrate-bullmq	Migrate from BullMQ to glide-mq - API mapping, breaking changes, feature comparison
glide-mq-migrate-bee	Migrate from Bee-Queue to glide-mq - API mapping, pattern conversion

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:

Agent	Model	Role
task-discoverer	sonnet	Finds and ranks tasks from your source
worktree-manager	haiku	Creates git worktrees and branches
exploration-agent	sonnet	Deep codebase analysis before planning
planning-agent	opus	Designs step-by-step implementation plan
implementation-agent	opus	Writes the actual code
prepare-delivery:test-coverage-checker	sonnet	Validates tests exist and are meaningful
prepare-delivery:delivery-validator	sonnet	Final checks before shipping
ci-monitor	haiku	Watches CI status
ci-fixer	sonnet	Fixes CI failures and review comments
simple-fixer	haiku	Executes mechanical edits

Cross-plugin agent: | Agent | Plugin | Role | |-------|--------|------| | deslop-agent | deslop | Removes AI artifacts before review | | sync-docs-agent | sync-docs | Updates documentation |

Usage:

```bash /next-task