agentrigs
+ submit rig
~ / rigs / MagicalYuYu / agent-operating-system

MagicalYuYu/agent-operating-system

AOS — Agent Operating System: 运行在类 Claude Code agent harness 上的个人文件治理层（DSH 完整适配 / AGENTS.md 工具通用适配）

↗ GitHub ★ 4 NOASSERTION updated 1d ago project Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.9k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/MagicalYuYu/agent-operating-system

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 MagicalYuYu/agent-operating-system/.dsh/skills/dual-machine .claude/skills/dual-machine
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/exa-search .claude/skills/exa-search
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/file-placement .claude/skills/file-placement
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/inspection .claude/skills/inspection
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/knowledge-ingest .claude/skills/knowledge-ingest
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/project-init .claude/skills/project-init
$ npx degit MagicalYuYu/agent-operating-system/.dsh/skills/subagent-dispatch .claude/skills/subagent-dispatch

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)

dual-machineexa-searchfile-placementinspectionknowledge-ingestproject-initsubagent-dispatch

Similar rigs

aerovato/operator-memory
The self-improving context engine for coding agents.
★ 68 project Claude Code 7 skills 7d ago
Pragmatist 166 tok ·
Jeong-Jae-Hun/dev-setup-template
Claude Code + dotfiles + 옵시디언(PARA) 통합 워크플로우 템플릿
★ 0 setup Claude CodeCodex 7 skills 9mo ago
Pragmatist 481 tok ·
ecodelearn/template-claude-code-open
Multi-agent coding template — persistent memory, spec-driven workflow, skills and security hooks for Claude Code, Cursor, Windsurf, GitHub Copilot and any AGENTS.md-reading tool. No dependencies.
★ 24 project Claude CodeCodex 9 skills 3 agents 2 hooks 2mo ago
Pragmatist 1.4k tok ·
fabriqaai/specs.md
specs.md - ai-dlc spec driven development framework
★ 208 project Claude Code 15 skills 1mo ago
Skill Collector 2.2k tok ·
copied ✓