Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add voxpelli/vp-claudenpx agentmods add plugins/voxpelli/vp-claude/vp-claudegit clone --depth 1 https://github.com/voxpelli/vp-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/voxpelli/vp-claude/vp-claude)<a href="https://agentmods.dev/plugins/voxpelli/vp-claude/vp-claude"><img src="https://agentmods.dev/badge/plugins/voxpelli/vp-claude/vp-claude.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
vp-knowledge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "vp-knowledge",
"version": "0.34.2",
"description": "Basic Memory power tools: multi-ecosystem package research (npm, Rust, Go, PHP, Python, Ruby), developer tool research (Homebrew, GitHub Actions, Docker, VSCode, gh CLI extensions, Claude Code plugins, skills.sh bundles), person research, knowledge gap analysis, project context priming, knowledge exploration, Readwise integration, schema evolution, tag alignment, graph maintenance, and automated quality hooks.",
"author": {
"name": "Pelle Wessman",
"url": "https://github.com/voxpelli"
},
"repository": "https://github.com/voxpelli/vp-claude",
"license": "MIT",
"keywords": [
"basic-memory",
"knowledge-graph",
"npm",
"research",
"crates",
"pypi",
"go-modules",
"composer",
"rubygems",
"multi-ecosystem",
"homebrew",
"github-actions",
"docker",
"vscode",
"tool-intel",
"claude-plugin",
"skills"
]
}
What it installs
The manifest is a name and a version. 14 skills, 5 agents, 4 hooks travel with it, and installing the plugin installs all of them — 2,851 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill knowledge-gaps A 185 tokens
- Skill people-intel A 118 tokens
- Skill schema-evolve A 139 tokens
- Skill knowledge-maintain A 183 tokens
- Skill raindrop-triage A 181 tokens
- Skill knowledge-garden A 152 tokens
- Skill knowledge-prime A 128 tokens
- Skill nudge A 210 tokens
- Skill session-bookmarks A 129 tokens
- Skill session-reflect A 147 tokens
- Skill tag-sync A 126 tokens
- Skill knowledge-ask A 142 tokens
- Skill intel A 244 tokens
- Skill vp-note-quality A 49 tokens
- Agent knowledge-gardener A 135 tokens
- Agent knowledge-maintainer A 173 tokens
- Agent raindrop-gardener A 123 tokens
- Agent knowledge-primer A 131 tokens
- Agent finding-verifier A 156 tokens
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook SessionStart A not measured
- Hook PreToolUse A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 31 lines scan A 9530c4d66eec
vp-knowledge is a plugin published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
vp-beads
Sprint workflow automation: backlog grooming, retrospectives, upstream vendor tracking, cross-project synergy tracking, swarm wave orchestration, vendor sync, and bilateral sibling reconciliation for projects using beads and Basic Memory.
claude-wiki-pages
A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.
membrain
Graph-based agent memory — search, trace, and manage what your agent knows.
capture
Capture session information into a staging file for later reflection and knowledge graph processing.
neatcontext marketplace
Save Claude Code work as reusable, domain-aware context.
neatcontext
Save Claude Code work as reusable, domain-aware context.