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.
git clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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/homenshum/nodebenchai/mcp-local)<a href="https://agentmods.dev/plugins/homenshum/nodebenchai/mcp-local"><img src="https://agentmods.dev/badge/plugins/homenshum/nodebenchai/mcp-local/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/homenshum/nodebenchai/mcp-local"><img src="https://agentmods.dev/badge/plugins/homenshum/nodebenchai/mcp-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nodebench-mcp 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 1mo 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": "nodebench-mcp",
"version": "2.30.0",
"description": "NodeBench MCP — 244-tool development methodology server with context sandbox, progressive discovery, agent-as-a-graph embeddings, and toolset gating presets.",
"author": {
"name": "Homen Shum",
"url": "https://github.com/homenshum"
},
"homepage": "https://github.com/homenshum/nodebench-ai#readme",
"repository": "https://github.com/homenshum/nodebench-ai",
"license": "MIT",
"keywords": [
"mcp",
"context-sandbox",
"fts5",
"bm25",
"progressive-discovery",
"agent-graph",
"embedding",
"toolset-gating",
"methodology"
],
"mcpServers": {
"nodebench-mcp": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/dist/index.js"]
}
},
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 2 skills, 2 hooks travel with it, and installing the plugin installs all of them — 86 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
4 files 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.
- 1mo ago First seen · 31 lines scan A f2554128144b
nodebench-mcp is a plugin published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 3d 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 2026-09-03.
Other plugins, from other repositories
hindsight-memory
Automatic long-term memory for Cursor via Hindsight. Recalls relevant memories before each prompt and retains conversation transcripts after each response.
ultracontext
Cross-agent session portability. Powered by UltraContext.
knowl
Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.
context-guard
Per-session context-window observability. A mod writes each session's context-window figures to a snapshot file and shows the person a toast and a transcript line when the context zone (smart, acceptable or dumb, from bands in zones.json) worsens; with modelnotices on (off by default) it also tells Claude the zone at.
harness-memory
Keeps a repo's Claude Code memory layer healthy, against criteria from official Claude Code docs. audit checks CLAUDE.md, a root AGENTS.md, CLAUDE.local.md, .claude/rules/, and auto-memory for structure, size, placement, and index integrity, with scripted and judgment checks. stateless inspects, disables, and (after…
attestor
The memory layer for agent teams. Deterministic retrieval, hard per-project isolation, zero LLM in the critical path.