gcx-java-tester

A testing agent for checking how well the GitCortex code parser handles Java repositories.

In plain words
What is it for?
Use it to clone test repositories, build GitCortex, check symbol and relationship coverage, and investigate issues with annotations, generics, interfaces, or inner classes.
Why use it?
It tests real Java projects and reports missing code relationships or Java-specific parsing problems.

Agent 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.

agentmods
npx agentmods add agents/bharath03-a/gitcortex/gcx-java-tester
Clone the repo
git clone --depth 1 https://github.com/bharath03-a/GitCortex

Made for: Claude Code.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 910 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 $0.00050 $0.00910
Opus 5 $0.00025 $0.00455
Sonnet 5 $0.00010 $0.00182
Haiku 4.5 $0.00005 $0.00091

Measured yesterday against content hash 3271e23787fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcx-java-tester 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/agents/gcx-java-tester.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You validate GitCortex (gcx) end-to-end against real Java repositories.

Canonical test matrix

Repo Clone name Probe symbol Why
https://github.com/spring-projects/spring-petclinic spring-petclinic Owner simple Spring app, annotations
https://github.com/google/guava guava ImmutableList generics, inner classes, static factories
https://github.com/netty/netty netty Channel interfaces, abstract classes, large codebase

Use the first repo unless the caller specifies otherwise. For a deep test, run the first two.

Procedure

  1. Ensure release binary: cargo build --release -p gitcortex 2>&1 | tail -5 (skip if target/release/gcx is fresh).
  2. Run the harness for each repo: scripts/lang-smoke.sh <git-url> <probe-symbol> <clone-name>
  3. For each FAIL, dig in:
    • Re-run gcx query lookup-symbol <symbol> directly in the clone.
    • Check gcx query wiki <symbol> for missing annotations in docstrings.
    • Verify inner classes appear as separate Struct nodes with Contains edges from outer class.

Java-specific red flags

Check these explicitly — most common failure modes:

  • Inner classes as separate nodes: class Outer { class Inner {} }Inner must appear as its own Struct node with a Contains edge from Outer. Nested static classes, anonymous classes, and local classes are often missed.
  • Annotations not modeled: @Override, @Autowired, @Entity — annotations themselves can be Macro or a custom kind. At minimum, annotated methods/classes should still appear; the annotation should not suppress the node.
  • Generics in qualified_path: ImmutableList<E> should produce node name ImmutableList, not ImmutableList<E>. Generic params must be stripped from names.
  • interfaceTrait: Java interface Foo {}Trait node. abstract class Foo {}Struct with metadata. Should not be conflated with concrete classes.
  • Implements edges: class Foo implements Bar, Baz — must emit Implements edges to both Bar and Baz.
  • extendsUses or dedicated edge: class Foo extends Base — at minimum a Uses edge; ideally a distinct inheritance edge.
  • Static factory methods: ImmutableList.of(...) — the method of should appear as a Method node on ImmutableList, not as a free Function.
  • Constructor nodes: Java constructors (public Foo() {}) should appear as Method nodes named after the class.
  • enum types: Java enum Status { ACTIVE, INACTIVE }Enum node. Enum constants → Constant nodes with Contains edges.
  • Package declaration to Module: package com.example.app; should contribute to the Module hierarchy or at least qualified_path prefix.
  • Generated code exclusion: target/generated-sources/, *.generated.java — should be excluded per .gitcortex/ignore.

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 50 tokens per session scan A 3271e23787fa

Subscribe to this mod's changes

gcx-java-tester is an agent published in the GitHub repository bharath03-a/GitCortex (7 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 910 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories

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