Agentix CEO Skill - Setup Guide¶

Source: agentix-cloud/skills GitHub: agentix-cloud/skills Skills: 1 skill (agentix-ceo) · 52.0K installs Category: Multi-Agent Orchestration First Seen: March 20, 2026 (catalogued August 15, 2026 sweep) Quality Tier: 🟡 Trusted (Gen Agent Trust Hub pass, Socket pass; Snyk reports a warning)

agentix-ceo turns the agent into a CEO that orchestrates a team of AI workers through the Agentix platform. Workers are ephemeral agents spawned on Modal that complete their task and exit. The skill supports two operating modes: supervised (user approval for new work) and autopilot (full autonomous planning and execution). Roles carry custom system prompts, tasks carry priority and status, and GitHub integration covers git-based workflows. Worker execution requires an Anthropic API key.

Installation¶

npx skills add agentix-cloud/skills --skill agentix-ceo

Prerequisites¶

Requirement	Details
Anthropic API key	Required for worker execution
Agentix endpoint	SaaS (`https://agentix.cloud`, default) or self-hosted URL via `AGENTIX_API_URL`
Node.js + npx	For the installer

# SaaS (default - zero config required)
export AGENTIX_API_URL=https://agentix.cloud

# Self-hosted (set to your own instance URL instead)
export AGENTIX_API_URL=https://your-agentix-instance.example.com

What It Provides¶

Capability	Notes
Role management	Create roles with custom system prompts
Task management	Create tasks with priority and status tracking
Ephemeral workers	Spawn workers on Modal that run and exit automatically
Operating modes	Supervised (approval gates) and autopilot (autonomous planning)
GitHub integration	Git-based workflows
Deployment options	SaaS (agentix.cloud with registration) or self-hosted (zero authentication)

Quick Start¶

npx skills add agentix-cloud/skills --skill agentix-ceo
Set AGENTIX_API_URL and the Anthropic key
Start supervised: "create a researcher role and assign it a task to summarize these three papers"
Graduate to autopilot only for tasks with reversible side effects

CorpusIQ Use Cases¶

Use Case	How
Research parallelism	Spawn ephemeral workers for multi-source market research sweeps
Task fan-out	Roles per workstream (research, drafting, review) with priority tracking
Orchestration reference	Supervised/autopilot mode design as a pattern for our own agent governance
Git workflows	Worker-driven git operations for docs and repo maintenance

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

Limitations / Verification¶

Requires an Anthropic API key for workers; Snyk audit carries a warning (review before production use)
Worker cost depends on Modal usage - budget per task

curl -s "$AGENTIX_API_URL" | head -c 200   # verify endpoint reachability

Skills Catalog
Ruflo Agent Orchestration - orchestration comparison

← Skills Catalog | Marketplace →

Powered by CorpusIQ