~ / rigs / Goldziher / basemind

Goldziher/basemind

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

↗ GitHub ★ 122 MIT updated 1d ago project CodexGemini CLI Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~6.1k tokens
Heavy · 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 ai-rulez -- ai-rulez mcp
$ npx degit Goldziher/basemind/skills ./rig-basemind/skills

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 ai-rulez -- ai-rulez mcp
$ npx degit Goldziher/basemind/.ai-rulez/skills/harness-canary-authoring .claude/skills/harness-canary-authoring
$ npx degit Goldziher/basemind/.ai-rulez/skills/index-keyspace-evolution .claude/skills/index-keyspace-evolution
$ npx degit Goldziher/basemind/.ai-rulez/skills/language-support .claude/skills/language-support
$ npx degit Goldziher/basemind/.ai-rulez/skills/mcp-tool-checklist .claude/skills/mcp-tool-checklist
$ npx degit Goldziher/basemind/.ai-rulez/skills/poly-and-release-workflow .claude/skills/poly-and-release-workflow
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-cli .claude/skills/basemind-cli
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-code-search .claude/skills/basemind-code-search
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-comms .claude/skills/basemind-comms
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-doctor .claude/skills/basemind-doctor
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-documents .claude/skills/basemind-documents
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-git-history .claude/skills/basemind-git-history
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-multi-agent-room .claude/skills/basemind-multi-agent-room
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-scan .claude/skills/basemind-scan
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind-stats .claude/skills/basemind-stats
$ npx degit Goldziher/basemind/.codex-plugin/skills/basemind .claude/skills/basemind

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 (2)

serversourceest. tokens
basemind local / custom 2.5k
ai-rulez binary 2.5k

Skills (15)

Similar rigs

copied ✓