agentrigs
+ submit rig
~ / rigs / heyramzi / ai-agency

heyramzi/ai-agency

41 agent skills, 5 slash commands and 1 agent for running an agency on Claude: an SEO kit, a YouTube production kit, a ClickUp delivery kit, and the two tools that keep a skills registry honest. Free courses at go.upsys-consulting.com/skool

↗ GitHub ★ 0 MIT updated today project Claude CodeCodexGemini CLI Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~548 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit heyramzi/ai-agency/agents ./rig-ai-agency/agents
$ npx degit heyramzi/ai-agency/commands ./rig-ai-agency/commands

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ curl -fsSL --create-dirs -o .claude/agents/project-manager.md https://raw.githubusercontent.com/heyramzi/ai-agency/main/agents/delivery/project-manager.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Subagents (1)

project-manager
model: sonnet
Runs client delivery on a ClickUp workspace end to end - intake, capacity, approvals and handover - by routing each stage to the ClickUp skills and the cu CLI. Use when work has to be scoped into a bo

Slash commands (6)

/clickup-foundations/marketing-department/seo-engine/start-here/the-project-manager/youtube-engine

Similar rigs

kdhhuns2000/claude-config
Claude Code 전역 설정 - Spring Boot 개발 가이드, 스킬, 에이전트, 훅
★ 1 setup Claude Code 2 skills 2 agents 1 hooks 8mo ago
Pragmatist 6.2k tok ·
pokaa3a/dotfiles-claude
—
★ 1 setup Claude Code 3 skills 1 agents 2mo ago
Minimalist 389 tok ·
sgbett/dotfiles-claude
—
★ 3 setup Claude Code 1 mcp 9 skills 3 agents 8d ago
YOLO Cowboy 6.4k tok ·
erewok/bmo-agent-setup
A CLI tool to configure a Claude Code environment with BMO.
★ 3 setup Claude Code 6 skills 9 agents 22d ago
Orchestrator 186 tok ·
copied ✓