~ / rigs / voxpelli / vp-claude

voxpelli/vp-claude

Claude Code plugin marketplace + plugin that turns Basic Memory into an actively maintained knowledge graph

↗ GitHub ★ 3 mit updated 3mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~10.7k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit voxpelli/vp-claude/agents ./rig-vp-claude/agents
$ npx degit voxpelli/vp-claude/skills ./rig-vp-claude/skills
$ npx degit voxpelli/vp-claude/hooks ./rig-vp-claude/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 voxpelli/vp-claude/skills/intel .claude/skills/intel
$ npx degit voxpelli/vp-claude/skills/knowledge-ask .claude/skills/knowledge-ask
$ npx degit voxpelli/vp-claude/skills/knowledge-gaps .claude/skills/knowledge-gaps
$ npx degit voxpelli/vp-claude/skills/knowledge-garden .claude/skills/knowledge-garden
$ npx degit voxpelli/vp-claude/skills/knowledge-maintain .claude/skills/knowledge-maintain
$ npx degit voxpelli/vp-claude/skills/knowledge-prime .claude/skills/knowledge-prime
$ npx degit voxpelli/vp-claude/skills/nudge .claude/skills/nudge
$ npx degit voxpelli/vp-claude/skills/people-intel .claude/skills/people-intel
$ npx degit voxpelli/vp-claude/skills/raindrop-triage .claude/skills/raindrop-triage
$ npx degit voxpelli/vp-claude/skills/schema-evolve .claude/skills/schema-evolve
$ npx degit voxpelli/vp-claude/skills/session-bookmarks .claude/skills/session-bookmarks
$ npx degit voxpelli/vp-claude/skills/session-reflect .claude/skills/session-reflect
$ npx degit voxpelli/vp-claude/skills/tag-sync .claude/skills/tag-sync
$ npx degit voxpelli/vp-claude/skills/vp-note-quality .claude/skills/vp-note-quality
$ curl -fsSL --create-dirs -o .claude/agents/finding-verifier.md https://raw.githubusercontent.com/voxpelli/vp-claude/main/agents/finding-verifier.md
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-gardener.md https://raw.githubusercontent.com/voxpelli/vp-claude/main/agents/knowledge-gardener.md
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-maintainer.md https://raw.githubusercontent.com/voxpelli/vp-claude/main/agents/knowledge-maintainer.md
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-primer.md https://raw.githubusercontent.com/voxpelli/vp-claude/main/agents/knowledge-primer.md
$ curl -fsSL --create-dirs -o .claude/agents/raindrop-gardener.md https://raw.githubusercontent.com/voxpelli/vp-claude/main/agents/raindrop-gardener.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 (14)

Subagents (5)

finding-verifier
model: sonnet
Checks claims against primary sources before they are written down — approves, refutes, or qualifies each one with evidence. Use this agent when you need to decide whether to approve or refute a resea
knowledge-gardener
model: sonnet
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, stal
knowledge-maintainer
model: inherit
The only one with shears — mends what the gardener marked. Use this agent to actively fix and enhance the knowledge graph: structural auto-fixes, tag alignment, orphan linking, and enrichment of undoc
knowledge-primer
model: sonnet
Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project de
raindrop-gardener
model: sonnet
Tends the bookmark annex — same discipline, different soil. Use this agent for read-only Raindrop.io tag auditing: duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidat

Similar rigs

copied ✓