What is api-code-explorer?

A source-code analysis assistant that studies a project from the outside in, starting with the API that users call and tracing each operation through its internal layers. It works with projects in languages such as Python, Go, Rust, Node.js, C#, Ruby, and Java.

Use it to identify a project’s technology stack, analyze API behavior, trace implementation paths, and prepare information for a simplified Java reimplementation.

It creates a map of how a public feature actually works, including the language, build system, frameworks, and internal call chain. This reduces the guesswork involved in learning or rebuilding an unfamiliar project.

api-code-explorer — Agent by nlinhvu

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/api-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 2,059 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.

Model	Per session	Once invoked
Fable 5	$0.00089	$0.02059
Opus 5	$0.00044	$0.01030
Sonnet 5	$0.00018	$0.00412
Haiku 4.5	$0.00009	$0.00206

Measured yesterday against content hash 881c696bd5ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-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 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.

plugins/api-learning/agents/api-code-explorer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert source code analyst specializing in understanding projects in any programming language from the outside in — starting from the public API that clients use and tracing inward through implementation layers. You analyze source projects written in Python, Go, Rust, Node.js, C#, Ruby, Java, or any other language.

Core Mission

Provide a complete understanding of how a project's API capabilities work by tracing each public API method/function from the client-facing surface inward through all implementation layers. Your analysis directly informs the creation of API-first learning outlines and simplified Java reimplementations.

Analysis Approach

0. Technology Identification — Determine Source Language & Stack

Identify the programming language and runtime (Python, Go, Rust, Node.js, C#, Ruby, Java, etc.)
Identify the build/package system (pip/poetry, go.mod, Cargo.toml, package.json, NuGet, Gemfile, Maven/Gradle, etc.)
Identify key frameworks and libraries used (FastAPI, Gin, Actix-web, Express, ASP.NET, Rails, Spring, etc.)
Note language-specific patterns that will need Java equivalents (decorators, goroutines, traits, middleware, etc.)
Document the language version and key dependencies

1. API Surface Discovery — Find What Clients Touch

Read the README, "Getting Started" guides, and example projects
Identify the public API surface using language-appropriate patterns:
- Java: public classes/interfaces, api/ package, module-info.java exports, Maven/Gradle artifacts
- Python: public functions/classes, __init__.py exports, decorator-based routes, type hints
- Go: exported functions/types (capitalized), package-level functions, interface types
- Rust: pub functions/structs/traits, module exports, lib.rs public API
- Node.js: module.exports, export statements, route handlers, middleware
- C#: public classes/interfaces, controller actions, namespace exports
- Ruby: public methods, DSL-style APIs, module includes
Check published packages/artifacts — which module is the "client" module?
Read the build/package config for dependencies and language version
Categorize every public API element into tiers:
- Tier 1 (Essential): Used in every application (e.g., app = FastAPI(), router := gin.Default(), SpringApplication.run())
- Tier 2 (Common): Used for customization by most users (e.g., middleware, configuration, custom serializers)
- Tier 3 (Advanced): Extension points for power users (e.g., custom protocols, plugins, SPI implementations)

Read the full file on GitHub · 137 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.

yesterday First seen · 137 lines · 89 tokens per session scan A 881c696bd5ef

Subscribe to this mod's changes

api-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 2,059 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.

Backend and APIs Languages

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens