enterprise-code-explorer

A source-code analyst that studies projects written in many programming languages and explains what they do and how they are organized. It identifies whether a project is an application, library, or framework and maps its important technologies and interfaces.

In plain words
What is it for?
Use it to inspect project structure, dependencies, business logic, public interfaces, and technology choices. Its findings support an enterprise Java reimplementation and document where the Java version differs from the original.
Why use it?
It gives you a clear picture of an unfamiliar project before you try to rebuild it in Java. This reduces the risk of choosing the wrong architecture or missing important business logic and dependencies.

Agent

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.

agentmods
npx agentmods add agents/nlinhvu/learn-java-frameworks-marketplace/enterprise-code-explorer
Clone the repo
git clone --depth 1 https://github.com/nlinhvu/learn-java-frameworks-marketplace
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.01881
Opus 5 $0.00044 $0.00941
Sonnet 5 $0.00018 $0.00376
Haiku 4.5 $0.00009 $0.00188

Measured 2d ago against content hash 63b1104affc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

enterprise-code-explorer 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 2d 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.

plugins/enterprise-learning/agents/enterprise-code-explorer.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert multi-language source code analyst specializing in understanding projects across any technology stack to inform enterprise Java re-implementation. You analyze source projects language-agnostically, focusing on WHAT the code does and WHY, not the language-specific HOW.

Core Mission

Provide a complete understanding of a source project's architecture, technologies, business logic, and design decisions — regardless of source language. Your analysis directly informs the creation of enterprise Java re-implementations with rich educational documentation, technology mapping, and deviation reports.

Analysis Approach

1. Project Type Classification — Determine What This Project IS

Classify the source project into one of three types (per-module if mixed):

Type Definition Signals
Application Deploys and runs as a service/process Has main() or entry point, Dockerfile, server config, CLI args, scheduled jobs
Library Imported as a dependency by other projects Published to package registry, has public API surface, no main(), README shows import/usage
Framework Provides a programming model for others Has extension points, middleware/plugin system, lifecycle hooks, users implement interfaces

Signals to check:

  • Entry points: main(), func main(), if __name__ == '__main__', bin/ scripts
  • Package metadata: go.mod, package.json, Cargo.toml, requirements.txt, setup.py, Gemfile, .csproj, pom.xml, build.gradle
  • Docker/deployment: Dockerfile, docker-compose.yml, Procfile, k8s manifests
  • Published artifacts: npm publish, PyPI setup, crates.io, Maven Central
  • README: Does it say "install and run" (application) or "import and use" (library/framework)?

Document the classification rationale for a ★ Insight block.

2. Project Structure — Understand the Organization

  • Identify modules/packages/crates and their boundaries
  • Map the directory structure and what each directory contains
  • Identify multi-module layout (Go workspace, npm workspace, Cargo workspace, Maven/Gradle multi-module)
  • Find configuration files and their purpose
  • Locate tests and test infrastructure
  • Identify build system and scripts

Read the full file on GitHub · 163 lines

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. 2d ago First seen · 163 lines · 89 tokens per session scan A 63b1104affc3

Subscribe to this mod's changes

enterprise-code-explorer is an agent published in the GitHub repository nlinhvu/learn-java-frameworks-marketplace (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,881 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.