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 jaggernaut007/nexus-mcpnpx agentmods add plugins/jaggernaut007/nexus-mcp/plugingit clone --depth 1 https://github.com/jaggernaut007/nexus-mcpGrade A, and why
nexus-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 yesterday.
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": "nexus-mcp",
"displayName": "Nexus-MCP",
"description": "Hybrid search + code graph + semantic memory for Claude Code, via the nexus-mcp-ci pip package. Requires `pip install nexus-mcp-ci` first — this plugin registers the MCP server and teaches Claude when to use it, it does not install the Python package.",
"version": "2.0.0",
"author": {
"name": "Shreyas Jagannath",
"url": "https://github.com/jaggernaut007"
},
"homepage": "https://github.com/jaggernaut007/Nexus-MCP",
"repository": "https://github.com/jaggernaut007/Nexus-MCP",
"license": "MIT",
"keywords": ["code-search", "code-graph", "semantic-search", "mcp", "code-intelligence"]
}
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.
- yesterday First seen · 15 lines scan A 7cbbf5452199
nexus-mcp is a plugin published in the GitHub repository jaggernaut007/nexus-mcp (0 stars, last pushed 7d 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
roam-code
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
awesome-claude-notes
Battle-tested Claude Code configurations from an Anthropic hackathon winner — agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use.
agentmap
Single-plugin marketplace for agentmap — the queryable, PageRank-ranked ts-morph repo map for TS/JS coding agents.
agentmap
98% fewer context tokens for your coding agent to find code — a queryable, PageRank-ranked ts-morph import/symbol map for TS/JS repos. Bundles the PreToolUse grep nudge, the navigation skill, and a stdio MCP server exposing 11 query tools including a compiler-accurate call graph, BM25 lexical search, plus CLI-only Mer.
mako-ai
Project intelligence skills for Claude Code. Teaches Claude when to use Mako's MCP tools (context packets, code and schema search, diagnostics, RLS audits) instead of grep-walking the repo.
hello-world
A simple example plugin that demonstrates basic Claude Code plugin functionality.