sairenchristianbuerano/vault-graph
Live star map, task board and Claude Code memory hooks for your Markdown or Obsidian vault. Standard library Python, one HTML file.
stack: Python
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 sairenchristianbuerano/vault-graph/example-vault/.claude ./rig-vault-graph # 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 sairenchristianbuerano/vault-graph/example-vault/.claude/skills/changelog-writer .claude/skills/changelog-writer $ npx degit sairenchristianbuerano/vault-graph/example-vault/.claude/skills/triage-issue .claude/skills/triage-issue
$ curl -fsSL --create-dirs -o .claude/agents/docs-checker.md https://raw.githubusercontent.com/sairenchristianbuerano/vault-graph/main/example-vault/.claude/agents/docs-checker.md $ curl -fsSL --create-dirs -o .claude/agents/release-helper.md https://raw.githubusercontent.com/sairenchristianbuerano/vault-graph/main/example-vault/.claude/agents/release-helper.md $ curl -fsSL --create-dirs -o .claude/agents/vault-navigator.md https://raw.githubusercontent.com/sairenchristianbuerano/vault-graph/main/example-vault/.claude/agents/vault-navigator.md
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 *)"
]
}
} Skills (2)
Subagents (3)
| docs-checker | Reads the nightly link-checker report for docs-site and proposes fixes. |
| release-helper | Drafts the weekly release notes from merged PRs, following the release train rules. |
| vault-navigator model: haiku | Answers "what do we know about X" from this vault by running tools/vault.py and reading only the output. Read-only. |
Similar rigs
aden-hive/hive
Multi-Agent Harness for Production AI
Pragmatist 3.0k tok · · Q20
Jose-Ribeir/claude-code-review-gate
Native Claude Code AI code review + blocking pre-commit gate on your Claude subscription. Per-file reviewer subagents, severity/confidence verdicts. open-code-review, done compliantly.
Orchestrator 536 tok · · Q0
ekupekuAI/agenthub
The package manager and trust layer for agent skills: one command installs SKILL.md skills into Claude Code, Codex, Cursor and VS Code, scanned and capability-gated.
Skill Collector 521 tok · · Q0
jungrok5/ai-code-collaboration-best-practices
여러 AI 코딩 도구를 쓰는 팀을 위한 GitHub 협업 템플릿. 공통 규칙, 에이전트 스킬·훅, 사람 승인, CI·리뷰·이슈 자동화 제공
Fort Knox 20.0k tok · · Q38