agentrigs
+ submit rig
~ / rigs / mvschwarz / openrig

mvschwarz/openrig

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

↗ GitHub ★ 5,346 apache-2.0 updated 3d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.1k 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 mvschwarz/openrig/.claude ./rig-openrig  # inspect, then merge into .claude/

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 mvschwarz/openrig/.agents/skills/developing-openrig .claude/skills/developing-openrig
$ npx degit <redacted>-core/skills/agent-operated-software .claude/skills/agent-operated-software
$ npx degit <redacted>-core/skills/agent-operated-workflows .claude/skills/agent-operated-workflows
$ npx degit <redacted>-core/skills/applying-a-permission-policy .claude/skills/applying-a-permission-policy
$ npx degit <redacted>-core/skills/claude-compaction-restore .claude/skills/claude-compaction-restore
$ npx degit <redacted>-core/skills/delegating-work .claude/skills/delegating-work
$ npx degit <redacted>-core/skills/forming-an-openrig-mental-model .claude/skills/forming-an-openrig-mental-model
$ npx degit <redacted>-core/skills/loading-addressable-markdown .claude/skills/loading-addressable-markdown
$ npx degit <redacted>-core/skills/messaging-the-human .claude/skills/messaging-the-human
$ npx degit <redacted>-core/skills/mission-slice-sop .claude/skills/mission-slice-sop
$ npx degit <redacted>-core/skills/openrig-operating-model .claude/skills/openrig-operating-model
$ npx degit <redacted>-core/skills/openrig-skills .claude/skills/openrig-skills
$ npx degit <redacted>-core/skills/openrig-user .claude/skills/openrig-user
$ npx degit <redacted>-core/skills/orienting-to-an-inherited-seat .claude/skills/orienting-to-an-inherited-seat
$ npx degit <redacted>-core/skills/queue-handoff .claude/skills/queue-handoff
$ npx degit <redacted>-core/skills/refocusing .claude/skills/refocusing
$ npx degit <redacted>-core/skills/retiring-and-inheriting-a-seat .claude/skills/retiring-and-inheriting-a-seat
$ npx degit <redacted>-core/skills/seat-continuity-and-handover .claude/skills/seat-continuity-and-handover
$ npx degit <redacted>-core/skills/session-compaction-and-restore .claude/skills/session-compaction-and-restore
$ npx degit <redacted>-core/skills/software-for-agents .claude/skills/software-for-agents
$ npx degit <redacted> .claude/skills/rigs
$ npx degit <redacted>-specialist/skills/vault-user .claude/skills/vault-user

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

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

Skills (22)

developing-openrigagent-operated-softwareagent-operated-workflowsapplying-a-permission-policyclaude-compaction-restoredelegating-workforming-an-openrig-mental-modelloading-addressable-markdownmessaging-the-humanmission-slice-sopopenrig-operating-modelopenrig-skillsopenrig-userorienting-to-an-inherited-seatqueue-handoffrefocusingretiring-and-inheriting-a-seatseat-continuity-and-handoversession-compaction-and-restoresoftware-for-agentsrigsvault-user

Similar rigs

shreeve1/dotfiles
Cross-machine config: zsh, nvim, tmux, ghostty, plus agent guidance.
★ 0 setup Codex 147 skills 7d ago
Skill Collector 11.4k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
★ 180k collection Claude Code 19 skills 4d ago
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 149k project Claude Code 10 skills 6d ago
Skill Collector 1.4k tok ·
copied ✓