agentrigs
+ submit rig
~ / rigs / josherau / claude-operating-core

josherau/claude-operating-core

Quality gates for Claude Code: review-panel, focus-group pretesting, STORM research, extract-approach, and the advisor agent. The foundational skill pack behind an AI-operated multi-business setup.

↗ GitHub ★ 3 MIT updated 2mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~651 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 josherau/claude-operating-core/agents ./rig-claude-operating-core/agents
$ npx degit josherau/claude-operating-core/skills ./rig-claude-operating-core/skills

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.

$ npx degit josherau/claude-operating-core/skills/extract-approach .claude/skills/extract-approach
$ npx degit josherau/claude-operating-core/skills/focus-group .claude/skills/focus-group
$ npx degit josherau/claude-operating-core/skills/review-panel .claude/skills/review-panel
$ npx degit josherau/claude-operating-core/skills/sales-council .claude/skills/sales-council
$ npx degit josherau/claude-operating-core/skills/second-brain .claude/skills/second-brain
$ npx degit josherau/claude-operating-core/skills/storm-research .claude/skills/storm-research
$ npx degit josherau/claude-operating-core/skills/vault-gardener .claude/skills/vault-gardener
$ curl -fsSL --create-dirs -o .claude/agents/advisor.md https://raw.githubusercontent.com/josherau/claude-operating-core/main/agents/advisor.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 *)"
    ]
  }
}

Skills (7)

extract-approachfocus-groupreview-panelsales-councilsecond-brainstorm-researchvault-gardener

Subagents (1)

advisor
model: opus
High-intelligence strategic advisor (emulates Anthropic's advisor-tool pattern). Consult BEFORE committing to an approach on a multi-step task, BEFORE declaring a task done, and when stuck. Send a con

Similar rigs

luizsiqueira-eng/skills
Skills para agentes de IA (Claude Code): fluxos de engenharia neutros de empresa — npx @luizsiqueira/skills add <skill>
★ 1 collection Claude Code 5 skills 1mo ago
Pragmatist 430 tok ·
Rompomepome/amiral
The admiral doesn't row. Orchestrator/worker model routing for Claude Code: a capable brain plans and verifies, cheap hands execute. Works inside your plan.
★ 4 project Claude CodeCodex 1 skills 10 agents 3mo ago
Orchestrator 1.3k tok ·
vzsoares/dotfiles
Minimalistic dotfiles: Nvim - TMUX - zsh
★ 1 setup Claude Code 2 mcp 7 skills 2 hooks 2mo ago
Pragmatist 13.0k tok ·
rumotion/ai-agent-project-template
A portable template for AI coding projects: canonical AGENTS.md instructions, shared project memory, validated context, bounded worker reports and dependency-free tooling.
★ 1 project Claude CodeCodexCursor 11 skills 1 agents 6 hooks 6d ago
Fort Knox 2.5k tok ·
copied ✓