Agentsys plugin for Grok Build

Name: Agentsys
Author: agent-sh

Community Claude Code plugin, installs in GrokPluginAutomation

AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

How to install Agentsys in Grok Build

1. Add this repo as a plugin marketplace in Grok Build (once per computer):

grok plugin marketplace add agent-sh/agentsys

2. Install the plugin:

grok plugin install next-task@agent-sh/agentsys --trust

✓ Install-checked in Grok Buildchecked Oct 19, 2026

Review before you trust it. --trust lets this plugin's hooks, MCP servers and scripts run code on your computer. It's a community repo that neither xAI nor GrokStacks has reviewed, so read its code first.

This repo's marketplace has 25 plugins; we checked gate-and-ship, next-task, prepare-delivery. Install another the same way: grok plugin install <name>@agent-sh/agentsys --trust (names under 'What it contains'). Then start a new Grok session, or press r in /plugins, to load it.

Inside Grok Build: type /plugins, open the Marketplace tab, press a and add agent-sh/agentsys, then select next-task and press i.

Command format: Grok Build's plugin guide

What we checked: on Oct 19, 2026 it installed with grok 1.0.62 and Grok found 8 skills, 4 slash commands, 2 subagents. That's an install check only: we haven't run it in a live Grok session.

What it contains

Skills (8)

discover-tasks — Use when the user asks to discover tasks, find the next task, prioritize issues, or list open work. Discovers and ranks tasks from GitHub, GitHub Projects, GitLab, local task files, and custom sources.
delivery-approval — Validate task completion and approve for shipping. Can be used standalone or called by the workflow. Runs autonomous validation checks.
next-task — Master workflow orchestrator with autonomous task-to-production automation
check-test-coverage — Use when checking whether new or changed code has meaningful tests: tests exist, were updated with the change, and exercise the new behavior. Advisory; reports gaps, edits nothing.
orchestrate-review — Use for a deep, multi-pass code review of changed files, or as the review loop of a delivery pipeline. Parallel reviewers per concern, findings aggregated in code, fixes applied until clean.
prepare-delivery — Use when the user asks to prepare delivery, run quality gates, deslop and review, or validate before shipping. Runs local gates on the branch and reports readiness. Does not push.
validate-delivery — Use when the user asks to validate delivery, check readiness, or verify a branch is done. Runs tests and build, checks the task's requirements and review status, returns approve or fix instructions.
gate-and-ship — Quality gates then ship - runs /prepare-delivery then /ship in one command. Use after completing implementation to go from code to merged PR.

Subagents (11)

next-task:worktree-manager — Create an isolated git worktree and feature branch for a /next-task task. Use after task selection.
next-task:task-discoverer — Use when /next-task needs candidate tasks after policy selection, or the user asks to discover, rank, or list open tasks. Fetches, filters, and scores tasks from the configured source and returns the
next-task:simple-fixer — Apply a pre-computed list of mechanical edits (remove line, replace text, insert line) and commit them. Use when deslop or sync-docs returns fixes to apply.
next-task:planning-agent — Design an implementation plan for a /next-task task from the exploration report and return it as structured JSON for the orchestrator to present for approval. Use after exploration.
next-task:implementation-agent — Implement an approved /next-task plan in its worktree, with tests, as local commits. Use after the user approves the plan.
next-task:exploration-agent — Explore the codebase for a /next-task task before planning. Finds the files to change, the patterns to follow, dependencies, and risks, and returns a report the planner can use without re-exploring.
next-task:ci-monitor — Watch a PR's CI checks and review comments until they settle, then report what needs fixing. Use after a PR is open when you want monitoring delegated to a fast, cheap agent.
next-task:ci-fixer — Fix one CI failure or one PR review comment that needs a code change, commit it, and push the PR branch. Use from /ship or ci-monitor when a check fails or a reviewer asks for a change.
prepare-delivery:test-coverage-checker — Check that code changed on a branch has meaningful tests that exercise it, not just a test file with a matching name. Advisory, read-only; runs before the first review round.
prepare-delivery:prepare-delivery-agent — Run the pre-ship quality gates (deslop, config lint, review loop, delivery validation, docs sync) on the current branch and return a PREPARE_DELIVERY_RESULT block. Local only; never pushes.
prepare-delivery:delivery-validator — Decide whether a reviewed branch is ready to ship. Runs tests and build, checks requirements and review status, and returns approval or fix instructions. Used by /prepare-delivery and /next-task after

Hooks (1)

hooks — SubagentStop

Plugins in this marketplace (25)

next-task — Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 8 specialist agents
prepare-delivery — Pre-ship quality gates: deslop, simplify, agnix, enhance, review loop, delivery validation, docs sync
gate-and-ship — Quality gates then ship - chains /prepare-delivery then /ship in one command
ship — Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback
deslop — 3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)
audit-project — Multi-agent iterative code review until zero issues remain
drift-detect — Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans
enhance — Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting
skill-curator — Canonical guidance for writing, reviewing, and maintaining production-grade SKILL.md files across agent tools
system-prompt-curator — Production-grade system prompt curation for autonomous coding agents and multi-agent orchestration
sync-docs — Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes
repo-intel — Unified static analysis via agent-analyzer - git history, AST symbols, project metadata, and doc-code sync
perf — Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions
learn — Research topics online and create comprehensive learning guides with RAG-optimized indexes
banthis — Durable negative behavior memory: persist user-defined banned agent behaviors into CLAUDE.md or AGENTS.md
agnix — Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 457 rules across 10+ AI tools
consult — Cross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control
debate — Structured multi-round debate between AI tools with proposer/challenger roles and verdict
skillers — Learn from workflow patterns across sessions and suggest skills, hooks, and agents to automate repetitive work
onboard — Codebase onboarding - automated data collection and interactive project orientation
can-i-help — Find where to contribute to any project - matches developer skills to test gaps, stale docs, bugspots, and open issues
tower-crane — Hand over an issue, a goal or a whole project: plan into tasks, dispatch workers, clean-context review, software gates and merges. Needs the tower-crane CLI on PATH
zig-lsp — Zig language server for Claude Code via ZLS - automatic diagnostics after every edit, jump-to-definition, find-references, and hover. Requires zls in PATH
mojo — Teach agents to write idiomatic, correct, performant, current Mojo (v1.0.0b1) - syntax, ownership and CPU/memory optimization (copies, SIMD, vectorize/parallelize), GPU kernels (DeviceContext/LayoutTensor), and Mojo/Python interop; prevents stale pre-2025 syntax
ada-spark — Teach agents to write idiomatic, correct, current Ada and SPARK (Ada 2022) - contracts (aspects, Pre'Class), the Alire ecosystem, SPARK proof (AoRTE, assurance levels, ownership/borrow), embedded (Ravenscar/Jorvik), and GNAT/GNAT SAS tooling; blocks stale pre-2022 advice (GNAT Community, pragma cont

About this listing

Agentsys is a community plugin on GitHub by agent-sh, written as a Claude Code plugin that Grok Build installs. We install-checked it in Grok; we haven't run it in a live session or reviewed its code. When we installed it, Grok found 8 skills, 11 subagents, 1 hook, 25 plugins in this marketplaces. Its license is MIT. We checked commit 2c9f607d48c4. It's one of 82 listings in the Automation category on GrokStacks.

Agentsys FAQ

How do I install Agentsys in Grok Build?

Add the repo as a marketplace with grok plugin marketplace add agent-sh/agentsys, then run grok plugin install next-task@agent-sh/agentsys --trust. This repo's marketplace has 25 plugins; we checked gate-and-ship, next-task, prepare-delivery. Install another the same way: grok plugin install <name>@agent-sh/agentsys --trust (names under 'What it contains'). Then start a new Grok session, or press r in /plugins, to load it.

Is Agentsys an official Grok Build plugin?

No. Agentsys is a community plugin on GitHub by agent-sh, not in xAI's official Grok Build marketplace. We checked that it installs and what Grok loads from it, but haven't run it in a live Grok session or reviewed its code.

What does Agentsys include?

According to what Grok loaded in our install check, Agentsys includes 8 skills, 11 subagents, 1 hook, 25 plugins in this marketplaces: discover-tasks, delivery-approval, next-task, check-test-coverage, orchestrate-review, prepare-delivery….

Details

Type: Plugin
Category: Automation
Source: Community Claude Code plugin, installs in Grok
License: MIT
Author: agent-sh
Version: 6.1.1
Keywords: agent, ai, anthropic, automation, autonomous-agents, claude, claude-code, cli, code-review, codex, cursor, devtools
Source repo: https://github.com/agent-sh/agentsys
Checked commit: 2c9f607d48c4
Homepage: https://agent-sh.github.io/agentsys/
Checked by GrokStacks: Install-checked in Grok Build on Oct 19, 2026; not run in a live session

Something wrong or missing? Submit or improve this listing. Marketplace listings also refresh automatically every night.

For maintainers: badge and embeds

Maintain Agentsys? Add the badge; it links to this page.

Markdown

[![Listed on GrokStacks](https://grokstacks.com/badge.svg)](https://grokstacks.com/p/agentsys/)

HTML

<a href="https://grokstacks.com/p/agentsys/"><img src="https://grokstacks.com/badge.svg" alt="Listed on GrokStacks" width="164" height="28"></a>

Embed card (static HTML and inline CSS, no JavaScript). Preview:

AgentsysCommunity plugin for Grok Build · 8 skills, 11 subagents, 1 hook, 25 plugins in this marketplacesAI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode…View on GrokStacks →

<a href="https://grokstacks.com/p/agentsys/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #2a2e3c;border-radius:12px;background:#0a0b0f;color:#e8eaf0;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#e8eaf0">Agentsys</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 8 skills, 11 subagents, 1 hook, 25 plugins in this marketplaces</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>

Markdown summary

**[Agentsys on GrokStacks](https://grokstacks.com/p/agentsys/)**: Community plugin for Grok Build with 8 skills, 11 subagents, 1 hook, 25 plugins in this marketplaces. Install: `grok plugin install next-task@agent-sh/agentsys --trust` (after `grok plugin marketplace add agent-sh/agentsys`)

More on badges, embeds and keeping your listing up to date: GrokStacks for plugin authors.

Also in Automation

Agent Sop

Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.

Community Claude Code plugin, installs in GrokPluginAutomation

Agentic Creator Os

Agentic Creator OS (ACOS), by GenCreator: reusable orchestration, skills, commands, agents and local safety tooling for creator workflows.

Community plugin, built for Grok BuildPluginAutomation

Agentlas OS

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Community Claude Code plugin, installs in GrokPluginAutomationMCP: manual setup

Agentrq

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.

Community Claude Code plugin, installs in GrokPluginAutomationNeeds sign-in