Th0rgal/orb
All your AI providers, machines, and agent harnesses in one place. Formerly sandboxed.sh (now the backend to the Orb clients).
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Th0rgal/orb/.claude ./rig-orb # 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 Th0rgal/orb/skills/controllers-policy .claude/skills/controllers-policy $ npx degit Th0rgal/orb/skills/hermes-mission-control .claude/skills/hermes-mission-control $ npx degit Th0rgal/orb/skills/orchestrator-advisor .claude/skills/orchestrator-advisor $ npx degit Th0rgal/orb/skills/orchestrator-boss .claude/skills/orchestrator-boss $ npx degit Th0rgal/orb/skills/orchestrator-executor .claude/skills/orchestrator-executor $ npx degit Th0rgal/orb/skills/orchestrator-worker .claude/skills/orchestrator-worker $ npx degit Th0rgal/orb/skills/project-manager .claude/skills/project-manager $ npx degit Th0rgal/orb/skills/sandboxed-sh-missions .claude/skills/sandboxed-sh-missions
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 (8)
controllers-policyhermes-mission-controlorchestrator-advisororchestrator-bossorchestrator-executororchestrator-workerproject-managersandboxed-sh-missions
Permissions
deny (0)
—
ask (0)
—
allow (20)
Bash(cargo build:*)
Bash(cargo run:*)
Bash(cargo test:*)
Bash(cargo fmt:*)
Bash(cargo clippy:*)
Bash(bun:*)
Bash(cd dashboard && bun:*)
Bash(git:*)
Bash(ls:*)
Bash(cat:*)
Bash(mkdir:*)
Bash(cp:*)
Bash(mv:*)
Bash(jq:*)
Bash(python:*)
Read
Write
Edit
Glob
Grep
Similar rigs
senu-nk/project-manager
Turn vague ideas into developer-ready specs and vertical-slice build plans — one question at a time. A gated, resumable interview that adapts its depth to project complexity. It never invents requirements: unknowns become traceable Open Que
Minimalist 86 tok ·
nelson820125/iforgeai
13 specialized AI agents — PM, Architect, DBA, UI Designer, Project Manager, Frontend, .NET, QA, DevOps, Planner, Java, Python, DigitalTeam(coordinator) — forming a structured software delivery team with defined handoffs, gate reviews, and
Skill Collector 14.4k tok ·
Eflarus/claude-dotfiles
Opinionated Claude Code dotfiles — global standards, custom agents, RFC workflow, skills, hooks & statusline
Skill Collector 2.1k tok ·
tronghieu/agent-skills
Method-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any agentskills.io-compatible agent.
Skill Collector 1.9k tok ·