A local code map for coding agents that indexes files and relationships between symbols, such as who calls a function or what a function calls. It keeps the map updated as files change and adds architecture context, including module links and crate dependencies.

Use it to explore a codebase, search for symbols or files, find callers and callees, and inspect project dependencies and architecture.

It reduces the need to read an unfamiliar codebase file by file before finding relevant code. The agent can search the current structure and trace connections between parts of the project.

oxcode — Plugin by oxgraph

Install

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.

Claude Code

/plugin marketplace add oxgraph/oxcode

agentmods

npx agentmods add plugins/oxgraph/oxcode/claude-plugin

Clone the repo

git clone --depth 1 https://github.com/oxgraph/oxcode

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

oxcode 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.

claude-plugin/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "oxcode",
  "version": "0.4.2",
  "description": "PageRank-curated code intelligence for coding agents. Bundles the oxcode MCP server over stdio (self-updating from v0.1.2): oxcode_watch builds the index and keeps it current as files change — a file lock elects a single writer per folder while other instances serve reads; explore/search/callers/callees/symbol/files/status query it. explore also surfaces n-ary impl/module hyperedges and a crate dependency graph for architecture-altitude context.",
  "author": { "name": "oxgraph", "email": "[email protected]" },
  "homepage": "https://oxgraph.io",
  "repository": "https://github.com/oxgraph/oxcode",
  "license": "MIT",
  "keywords": ["mcp", "code-intelligence", "code-navigation", "pagerank", "oxgraph"]
}

Changes

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 · 11 lines scan A 4de7b0f8f72f

Subscribe to this mod's changes

oxcode is a plugin published in the GitHub repository oxgraph/oxcode (3 stars, last pushed 14d 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.

Planning Research

oxcode

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc