~ / rigs / smart-coder-labs / nexus-mind

smart-coder-labs/nexus-mind

Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.

↗ GitHub ★ 2 MIT updated 9d ago project Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~4.9k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 15/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add nexusmind -e NEXUSMIND_<redacted> -e NEXUSMIND_BASE_URL=YOUR_NEXUSMIND_BASE_URL -- npx -y @smart-coder-labs/nexusmind-mcp
$ npx degit smart-coder-labs/nexus-mind/.claude ./rig-nexus-mind  # 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.

$ claude mcp add nexusmind -e NEXUSMIND_<redacted> -e NEXUSMIND_BASE_URL=YOUR_NEXUSMIND_BASE_URL -- npx -y @smart-coder-labs/nexusmind-mcp
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/coding-agent .claude/skills/coding-agent
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/dust-react-hook-form-writer .claude/skills/dust-react-hook-form-writer
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/frontend-patterns .claude/skills/frontend-patterns
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/playwright-cli .claude/skills/playwright-cli
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/product-inventor .claude/skills/product-inventor
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/react-hook-form-zod .claude/skills/react-hook-form-zod
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/receiving-code-review .claude/skills/receiving-code-review
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/shadcn .claude/skills/shadcn
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/web-artifacts-builder .claude/skills/web-artifacts-builder
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/web-design-reviewer .claude/skills/web-design-reviewer
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/webapp-testing .claude/skills/webapp-testing
$ npx degit smart-coder-labs/nexus-mind/.claude/skills/zod-4 .claude/skills/zod-4

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

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

MCP servers (1)

serversourceest. tokens
@smart-coder-labs/nexusmind-mcp · "nexusmind"
env: NEXUSMIND_API_KEY, NEXUSMIND_BASE_URL
npm 2.5k

Skills (13)

Hooks (1)

eventmatcherruns
SessionStart*bash scripts/nm-context.sh

Similar rigs

copied ✓