Elnora-AI/knowledge-vault
Obsidian vault power tools for Claude Code — search and save your work to any vault. Config-driven, universal, one-line install.
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 Elnora-AI/knowledge-vault/agents ./rig-knowledge-vault/agents $ npx degit Elnora-AI/knowledge-vault/commands ./rig-knowledge-vault/commands $ npx degit Elnora-AI/knowledge-vault/skills ./rig-knowledge-vault/skills $ npx degit Elnora-AI/knowledge-vault/hooks ./rig-knowledge-vault/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.
$ npx degit Elnora-AI/knowledge-vault/skills/agent-coordination .claude/skills/agent-coordination $ npx degit Elnora-AI/knowledge-vault/skills/file-naming .claude/skills/file-naming $ npx degit Elnora-AI/knowledge-vault/skills/vault-access .claude/skills/vault-access
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-agent.md https://raw.githubusercontent.com/Elnora-AI/knowledge-vault/main/agents/knowledge-agent.md $ curl -fsSL --create-dirs -o .claude/agents/vault-curator.md https://raw.githubusercontent.com/Elnora-AI/knowledge-vault/main/agents/vault-curator.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 *)"
]
}
} Skills (3)
Subagents (2)
| knowledge-agent model: haiku | Manages Obsidian vault access - fetch documents, create versioned files, search notes/documents/templates, build Bases dashboards (.base), and create Canvas diagrams (.canvas). Uses Glob/Grep/Read/Wri |
| vault-curator model: sonnet | Persists a work session's results into the Obsidian vault — investigates the current structure, decides the correct folders (creating folders/subfolders only when genuinely needed), then creates or up |
Slash commands (8)
/kb-setup/md/note/task-done/task-triage/task/tasklist/update-knowledgebase
Similar rigs
354685856-sn/cat-codex
My AI agent team workflow harness — built on the SAFe Agentic Workflow template (multi-provider: Claude Code, Gemini, Codex, Cursor).
Orchestrator 16.0k tok ·
codemirket/harness
Reusable agent skills, project workflows and executable verification tools for Codex Desktop and Claude Desktop Code.
Skill Collector 7.4k tok ·
manishiitg/agentworks
AgentWorks: AI agents that own the work. Goals that chase a metric, and Crews your team asks from Claude, ChatGPT or Cursor. Open source.
Skill Collector 3.3k tok ·
a5c-ai/babysitter
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
Skill Collector 14.3k tok ·