ai-codebase-intelligence

A codebase analysis plugin that understands source code in 13 languages and maps relationships between code elements. It also searches code and analyzes Git history, such as ownership, change frequency, and unused code.

In plain words
What is it for?
Finding related code, exploring how parts of a repository connect, identifying ownership and bus-factor risks, studying code churn and co-change patterns, and locating dead code.
Why use it?
It helps an assistant investigate a large codebase and its history without relying only on plain-text search.

Plugin for Claude Code

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 cdeust/ai-architect-mcp
agentmods
npx agentmods add plugins/cdeust/ai-architect-mcp/ai-codebase-intelligence
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp

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

ai-codebase-intelligence 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.

ai-codebase-intelligence/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "ai-codebase-intelligence",
  "description": "Language-agnostic codebase intelligence — 17 MCP tools, tree-sitter parsing for 13 languages, typed Pydantic graph API, BM25 + RRF hybrid search, and 5 science-backed git analytics (ownership, bus factor, churn, cochange, dead code).",
  "version": "0.1.0",
  "author": {
    "name": "Clement Deust",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/cdeust/ai-architect-mcp",
  "repository": "https://github.com/cdeust/ai-architect-mcp",
  "license": "MIT",
  "keywords": ["mcp", "codebase-intelligence", "static-analysis", "tree-sitter", "graph", "git-analytics", "claude-code", "anthropic"],
  "mcpServers": {
    "ai-codebase-intelligence": {
      "command": "uvx",
      "args": ["--python", "3.12", "--from", "ai-automated-codebase-intelligence", "ai_codebase_intelligence_mcp"]
    }
  }
}
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.

  1. yesterday First seen · 20 lines scan A 44bf00c14e78

Subscribe to this mod's changes

ai-codebase-intelligence is a plugin published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo 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.

Related

Other plugins, from other repositories

goalkeeper

Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, and linear chains.

bonfire-systems/goalkeeper · not measured

polisade-marketplace

Plugin marketplace listing 1 plugin: polisade.

cryndoc/polisade-orchestrator · not measured

milestone-driver

Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…

kenmulford/milestone-driver · not measured

shiploop

Single-plugin marketplace for shiploop — a self-improving multi-agent harness (every resolved ticket writes a lesson into your git-tracked CLAUDE.md) that grinds your ticket backlog across every repo in your product.

anshss/shiploop · not measured

devlens

Codebase intelligence for AI agents. The /devlens skill teaches your agent to query a precomputed code graph (nodes, typed edges, technical/business/security summaries) via the bundled DevLens MCP server instead of grepping and reading whole files — for TypeScript, JavaScript, Python, Go, Rust, and Java repos, with…

devlensio/devlensOSS · not measured

cc-autopilot

Autonomous judge agents fix your app's debt, build what's missing, and verify every change through a browser or gate suite before it lands, then find the next thing and keep going until you say stop. Each fixer owns a file-disjoint slice of the tree, so no two can ever collide, and nothing unverified reaches git. A…

gbotev1/cc-autopilot · not measured