sipyourdrink-ltd/bernstein
The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add bernstein -- bernstein mcp $ npx degit sipyourdrink-ltd/bernstein/agents ./rig-bernstein/agents $ npx degit sipyourdrink-ltd/bernstein/commands ./rig-bernstein/commands $ npx degit sipyourdrink-ltd/bernstein/skills ./rig-bernstein/skills $ npx degit sipyourdrink-ltd/bernstein/hooks ./rig-bernstein/hooks
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.
$ claude mcp add bernstein -- bernstein mcp $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-agents .claude/skills/bernstein-agents $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-alerts .claude/skills/bernstein-alerts $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-approve .claude/skills/bernstein-approve $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-cost .claude/skills/bernstein-cost $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-create-task .claude/skills/bernstein-create-task $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-plan .claude/skills/bernstein-plan $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-quality .claude/skills/bernstein-quality $ npx degit sipyourdrink-ltd/bernstein/packages/cursor-plugin/skills/bernstein-status .claude/skills/bernstein-status $ npx degit sipyourdrink-ltd/bernstein/skills/bernstein-run .claude/skills/bernstein-run $ npx degit sipyourdrink-ltd/bernstein/templates/skills/analyst .claude/skills/analyst $ npx degit sipyourdrink-ltd/bernstein/templates/skills/architect .claude/skills/architect $ npx degit sipyourdrink-ltd/bernstein/templates/skills/backend .claude/skills/backend $ npx degit sipyourdrink-ltd/bernstein/templates/skills/ci-fixer .claude/skills/ci-fixer $ npx degit sipyourdrink-ltd/bernstein/templates/skills/devops .claude/skills/devops $ npx degit sipyourdrink-ltd/bernstein/templates/skills/docs .claude/skills/docs $ npx degit sipyourdrink-ltd/bernstein/templates/skills/frontend .claude/skills/frontend $ npx degit sipyourdrink-ltd/bernstein/templates/skills/manager .claude/skills/manager $ npx degit sipyourdrink-ltd/bernstein/templates/skills/ml-engineer .claude/skills/ml-engineer $ npx degit sipyourdrink-ltd/bernstein/templates/skills/prompt-engineer .claude/skills/prompt-engineer $ npx degit sipyourdrink-ltd/bernstein/templates/skills/qa .claude/skills/qa $ npx degit sipyourdrink-ltd/bernstein/templates/skills/resolver .claude/skills/resolver $ npx degit sipyourdrink-ltd/bernstein/templates/skills/retrieval .claude/skills/retrieval $ npx degit sipyourdrink-ltd/bernstein/templates/skills/reviewer .claude/skills/reviewer $ npx degit sipyourdrink-ltd/bernstein/templates/skills/security .claude/skills/security $ npx degit sipyourdrink-ltd/bernstein/templates/skills/visionary .claude/skills/visionary $ npx degit sipyourdrink-ltd/bernstein/templates/skills/vp .claude/skills/vp
$ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/sipyourdrink-ltd/bernstein/main/agents/orchestrator.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| bernstein | binary | 2.5k |
Skills (26)
bernstein-agentsbernstein-alertsbernstein-approvebernstein-costbernstein-create-taskbernstein-planbernstein-qualitybernstein-statusbernstein-runanalystarchitectbackendci-fixerdevopsdocsfrontendmanagerml-engineerprompt-engineerqaresolverretrievalreviewersecurityvisionaryvp
Subagents (1)
| orchestrator | Decomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent. |
Slash commands (3)
/run/status/stop
Cursor rules (9)
architecture · alwaysbuild-test · alwaysdirectory-contextdocumentation-duty · alwaysgit-workflow · alwaysmodule-mapoverview · alwaysrolessetup · always
Similar rigs
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok ·
xiaobei930/cc-best
🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 40 commands · 17 skills · 8 agents · 33 rules · 21 hooks · auto-learning pipeline. | 一个插件，完整开发团队。
Orchestrator 2.0k tok ·
MarvelCollin/agent-skills
A growing collection of Claude Code skills, packaged as one plugin.
Minimalist 1.6k tok ·
Rhay427/D.StandarDev
An opinionated, portable Claude Code setup — engineering rules, five domain skills, and a tiered plugin install in one command.
Pragmatist 1.8k tok ·