Second Claude Code plugin for Grok Build

Name: Second Claude Code
Author: unclejobs-ai

Community plugin, built for Grok BuildPluginAutomation

God Hands — extra hands that find, analyze, plan, decompose, benchmark, and improve. The AI workflow that does not skip Check. 16 skills, 19 commands, 17 agents, 10 lifecycle hook events, and 3 MCP servers. /scc:godhands gathers, drafts, checks, and cuts.

How to install Second Claude Code in Grok Build

grok plugin install unclejobs-ai/second-claude-code --trust

✓ Install-checked in Grok Buildchecked Oct 18, 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.

We install this repo directly: Grok Build 1.0.62 can't install it through its own marketplace file. Then start a new Grok session, or press r in /plugins, to load it.

Command format: Grok Build's plugin guide

Runs a local MCP server (with npx, uvx or similar), so that tool needs to be installed, for example Node.js for npx.

What we checked: on Oct 18, 2026 it installed with grok 1.0.62 and Grok found 19 skills, 19 slash commands, 1 subagent. That's an install check only: we haven't run it in a live Grok session.

What it contains

Skills (19)

analyze — Use when analyzing a topic with a strategic framework, then stress-testing the plan against evidence
batch — Use when decomposing large tasks into independent parallel units that do not depend on each other
coach — Use when planning a fork: more than one defensible direction and no active standard covers it. Settle the plan before work starts. Do not use merely because a request is vague or underspecified; vagueness takes a clarifying question, not a
collect — Use when collecting URLs, notes, files, or excerpts into structured PARA knowledge
discover — Use when the current skills cannot handle a task and new skills are needed
evolve — Use when a prompt asset keeps causing the same PDCA gate failure and you want to evolve it against a maintainer-authored structural check
godhands — Use when a request needs extra hands that find, analyze, plan, decompose, benchmark, and improve through gated gather, draft, check, and cut. Do not use merely because a request is vague; vagueness takes a clarifying question, not a full pa
loop — Use when benchmarking and evolving prompt assets through a fixed-suite optimization loop
pdca — Use when running a PDCA cycle across research, production, review, and refinement
refine — Use when improving a draft until it meets a review target — the improve step after Check
research — Use when finding sources through iterative web exploration and synthesis
review — Use when benchmarking content, strategy, or code against a quality bar with parallel specialized reviewers
soul — Use when observing user patterns and synthesizing a persistent identity profile
translate — Use when translating content between English and Korean with formatting preservation
workflow — Use when chaining multiple /scc commands into a reusable workflow
write — Use when producing newsletters, articles, reports, shorts, or social content
standard-check — Run the project's active standards against one artifact and report every violation
unblock — Plan/Gather phase -- adaptive zero-key fetch chain for blocked or hardened web pages
viewer — Open the SCC Artifact Viewer, or export a PDCA session as a shareable provenance page

Subagents (15)

scc:knowledge-connector — Find specific shared concepts between new items and existing knowledge
scc:devil-advocate — Adversarial review that attacks the weakest points. Use when you want stress-testing before publishing or presenting. Examples: "Attack this proposal", "What would a skeptic say about this?", "Find th
scc:analyst — Data analysis and pattern recognition. Use after research collection to synthesize findings into structured insights. Examples: "Analyze these research findings", "Find patterns in this data", "Identi
scc:pipeline-orchestrator — Execute pipeline steps sequentially with state persistence
scc:skill-evaluator — Score skill candidates using weighted criteria
scc:editor — Content editing and quality improvement. Use when content exists and needs refinement based on feedback. Examples: "Improve the flow of this article", "Apply these review notes", "Tighten the argument
scc:researcher — Web search and data collection. Use when you need to gather information on a topic from multiple sources before analysis or writing. Examples: "Research competitor pricing", "Find recent stats on AI a
scc:tone-guardian — Tone and audience-fit review. Use when content must preserve a specific voice or match a target audience consistently. Examples: "Check whether this sounds like our newsletter voice", "Review tone con
scc:pipeline-step-executor — Execute a single pipeline step by reading input and writing output
scc:skill-inspector — Inspect skill candidates by reading their README and SKILL.md
scc:strategist — Strategic framework application. Use when you need structured strategic analysis using established frameworks. Examples: "SWOT analysis of our product", "Porter's Five Forces for the market", "Jobs-to
scc:skill-searcher — Search external sources for skills and packages
scc:soul-keeper — User soul observer and synthesizer — captures behavioral patterns across sessions, resolves contradictions as conditional rules, proposes soul evolution with evidence. Examples: "Synthesize my soul fr
scc:fact-checker — Fact and source verification. Use before publishing any content that contains statistics, quotes, dates, or factual claims. Examples: "Verify the stats in this article", "Check all claims in this repo
scc:writer — Long-form content creation. Use when you need polished written output based on research and analysis. Examples: "Write a newsletter about AI trends", "Draft a market analysis report", "Create a though

MCP servers (1)

pdca-state — stdio server

Hooks (1)

hooks — PostToolUse, PreCompact, SessionEnd, SessionStart, Stop, SubagentStop, UserPromptSubmit

About this listing

Second Claude Code is a community plugin on GitHub by unclejobs-ai, built for Grok Build. 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 19 skills, 15 subagents, 1 MCP server, 1 hook. Its license is MIT. We checked commit 75b28f25b57f. It's one of 82 listings in the Automation category on GrokStacks.

Second Claude Code FAQ

How do I install Second Claude Code in Grok Build?

Run grok plugin install unclejobs-ai/second-claude-code --trust. We install-checked this command in Grok Build. We install this repo directly: Grok Build 1.0.62 can't install it through its own marketplace file. Then start a new Grok session, or press r in /plugins, to load it.

Is Second Claude Code an official Grok Build plugin?

No. Second Claude Code is a community plugin on GitHub by unclejobs-ai, 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 Second Claude Code include?

According to what Grok loaded in our install check, Second Claude Code includes 19 skills, 15 subagents, 1 MCP server, 1 hook: analyze, batch, coach, collect, discover, evolve….

Details

Type: Plugin
Category: Automation
Source: Community plugin, built for Grok Build
License: MIT
Author: unclejobs-ai
Version: 3.1.2
Source repo: https://github.com/unclejobs-ai/second-claude-code
Checked commit: 75b28f25b57f
Checked by GrokStacks: Install-checked in Grok Build on Oct 18, 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 Second Claude Code? Add the badge; it links to this page.

Markdown

[![Listed on GrokStacks](https://grokstacks.com/badge.svg)](https://grokstacks.com/p/second-claude-code/)

HTML

<a href="https://grokstacks.com/p/second-claude-code/"><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:

Second Claude CodeCommunity plugin for Grok Build · 19 skills, 15 subagents, 1 MCP server, 1 hookGod Hands — extra hands that find, analyze, plan, decompose, benchmark, and improve. The AI workflow that does not…View on GrokStacks →

<a href="https://grokstacks.com/p/second-claude-code/" 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">Second Claude Code</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 19 skills, 15 subagents, 1 MCP server, 1 hook</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">God Hands — extra hands that find, analyze, plan, decompose, benchmark, and improve. The AI workflow that does not…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>

Markdown summary

**[Second Claude Code on GrokStacks](https://grokstacks.com/p/second-claude-code/)**: Community plugin for Grok Build with 19 skills, 15 subagents, 1 MCP server, 1 hook. Install: `grok plugin install unclejobs-ai/second-claude-code --trust`

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