GitCortex: Agent for Claude Code

.claude/agents/gcx-go-tester.md

gcx-go-tester is an agent for Claude Code from bharath03-a/GitCortex. It costs 50 tokens per session (879 once invoked), scanned A, original, MIT.

An end-to-end test workflow for gcx, a Go code parser and code-relationship indexer, using real open-source Go repositories.

In plain words
What is it for?
Use it to build gcx, clone representative Go projects, check symbol and relationship coverage, and investigate failed lookups or missing graph edges.
Why use it?
It reveals parser failures that small test files may miss, including problems with interfaces, embedded structs, middleware, generated code, or very large projects.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is bharath03-a/GitCortex's own configuration. It tells Claude Code how to work on GitCortex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything GitCortex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bharath03-a/GitCortex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bharath03-a/GitCortex/main/.claude/agents/gcx-go-tester.md
Clone the repo
git clone --depth 1 https://github.com/bharath03-a/GitCortex

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gcx-go-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-go-tester/github.svg)](https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-go-tester)
Your own site
<a href="https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-go-tester"><img src="https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-go-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gcx-go-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/bharath03-a/gitcortex/gcx-go-tester"><img src="https://agentmods.dev/badge/agents/bharath03-a/gitcortex/gcx-go-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.00879
Opus 5.5 $0.00020 $0.00352
Sonnet 5.5 $0.00010 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 2mo ago against content hash c6b0f3736643, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gcx-go-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 2mo 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.

.claude/agents/gcx-go-tester.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 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 Go repositories.

Canonical test matrix

Repo Clone name Probe symbol Why
https://github.com/gin-gonic/gin gin Engine struct + methods, middleware
https://github.com/grpc/grpc-go grpc-go ClientConn interfaces, embedding
https://github.com/kubernetes/kubernetes kubernetes Pod massive codebase, generated code

Use the first repo unless the caller specifies otherwise. For a deep test, run the first two (kubernetes is large).

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 edge counts for embedding — struct embedding is Go-specific and commonly missed.
    • Verify interface implementations are detected (Go has structural typing, not explicit implements).

Go-specific red flags

Check these explicitly — most common failure modes:

  • Struct embedding edges missing: type Server struct { http.Server } — the http.Server embedding should produce a Uses or dedicated edge to the embedded type. If the embedded field has no edge, embedding is not handled.
  • Interface satisfaction not detected: Go uses structural typing — type Foo struct{}; func (f Foo) Bar() {} satisfies interface { Bar() } implicitly. Implements edges require static analysis; at minimum, named interface types referenced in function signatures should have Uses edges.
  • Package-level functions vs. methods: func Foo() {} at package level → Function. func (r *Router) Foo() {} → Method with receiver. The receiver type should be the parent node for Contains.
  • Receiver pointer vs. value: func (r Router) F() and func (r *Router) F() both belong to Router. The * pointer receiver should not create a separate node.
  • init() functions: Should appear as Function nodes (multiple init per package is valid Go — qualify by file).
  • Multiple return values: Does not affect NodeKind but Uses edges should be emitted for all named return types.
  • type Alias = OriginalType: Go type aliases → TypeAlias node.
  • const blocks: const ( A = 1; B = 2 ) — each constant should be a separate Constant node.
  • Generated files: *.pb.go, *_gen.go, zz_generated_*.go — should be skipped per .gitcortex/ignore. Verify they don't bloat the graph.
  • qualified_path format: Go uses package paths — should be github.com/gin-gonic/gin::Engine::ServeHTTP not just Engine::ServeHTTP.

Read the full file on GitHub · 58 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. 2mo ago First seen · 58 lines · 50 tokens per session scan A c6b0f3736643

Subscribe to this mod's changes

gcx-go-tester is an agent published in the GitHub repository bharath03-a/GitCortex (8 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 879 once invoked, about $0.0002 per session on Opus 5.5. 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

test-engineer

Testing expert for .NET — test strategy, integration tests with WebApplicationFactory and Testcontainers, xUnit v3 patterns, and snapshot testing with Verify. Use when designing a test strategy, writing or fixing tests, setting up test infrastructure, or improving coverage of critical paths.

codewithmukesh/dotnet-claude-kit · 59 tokens

backend-go

Senior Go Engineer: Idiomatic Go services and tools: clear packages, context-aware concurrency, table-driven tests. Use for go, golang, goroutine, channel, grpc, go service work.

alvin-reyes/better-agentic-ide · 43 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 0 tokens

implementer-prompt

Implement one focused task in a Go codebase using strict test-driven development.

gopherguides/gopher-ai · 20 tokens

playwright-automation-engineer-ts-detailed

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.

jaktestowac/awesome-copilot-for-testers · 54 tokens

evolve-fuzz-probe

Fuzz testing runner and evaluator (Evaluate archetype).

mickeyyaya/evolve-loop · 18 tokens