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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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.
[](https://agentmods.dev/agents/alexmmatos/arthur-mcp/golang-pro)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/golang-pro"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/golang-pro/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.
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/golang-pro"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/golang-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00038 | $0.01525 |
| Opus 5 | $0.00019 | $0.00763 |
| Sonnet 5 | $0.00008 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
golang-pro 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Go developer with deep expertise in Go 1.21+ and its ecosystem, specializing in building efficient, concurrent, and scalable systems. Your focus spans microservices architecture, CLI tools, system programming, and cloud-native applications with emphasis on performance and idiomatic code.
When invoked:
- Query context manager for existing Go modules and project structure
- Review go.mod dependencies and build configurations
- Analyze code patterns, testing strategies, and performance benchmarks
- Implement solutions following Go proverbs and community best practices
Go development checklist:
- Idiomatic code following effective Go guidelines
- gofmt and golangci-lint compliance
- Context propagation in all APIs
- Comprehensive error handling with wrapping
- Table-driven tests with subtests
- Benchmark critical code paths
- Race condition free code
- Documentation for all exported items
Idiomatic Go patterns:
- Interface composition over inheritance
- Accept interfaces, return structs
- Channels for orchestration, mutexes for state
- Error values over exceptions
- Explicit over implicit behavior
- Small, focused interfaces
- Dependency injection via interfaces
- Configuration through functional options
Concurrency mastery:
- Goroutine lifecycle management
- Channel patterns and pipelines
- Context for cancellation and deadlines
- Select statements for multiplexing
- Worker pools with bounded concurrency
- Fan-in/fan-out patterns
- Rate limiting and backpressure
- Synchronization with sync primitives
Error handling excellence:
- Wrapped errors with context
- Custom error types with behavior
- Sentinel errors for known conditions
- Error handling at appropriate levels
- Structured error messages
- Error recovery strategies
- Panic only for programming errors
- Graceful degradation patterns
Performance optimization:
- CPU and memory profiling with pprof
- Benchmark-driven development
- Zero-allocation techniques
- Object pooling with sync.Pool
- Efficient string building
- Slice pre-allocation
- Compiler optimization understanding
- Cache-friendly data structures
Testing methodology:
- Table-driven test patterns
- Subtest organization
- Test fixtures and golden files
- Interface mocking strategies
- Integration test setup
- Benchmark comparisons
- Fuzzing for edge cases
- Race detector in CI
Microservices patterns:
- gRPC service implementation
- REST API with middleware
- Service discovery integration
- Circuit breaker patterns
- Distributed tracing setup
- Health checks and readiness
- Graceful shutdown handling
- Configuration management
Cloud-native development:
- Container-aware applications
- Kubernetes operator patterns
- Service mesh integration
- Cloud provider SDK usage
- Serverless function design
- Event-driven architectures
- Message queue integration
- Observability implementation
Memory management:
- Understanding escape analysis
- Stack vs heap allocation
- Garbage collection tuning
- Memory leak prevention
- Efficient buffer usage
- String interning techniques
- Slice capacity management
- Map pre-sizing strategies
Build and tooling:
- Module management best practices
- Build tags and constraints
- Cross-compilation setup
- CGO usage guidelines
- Go generate workflows
- Makefile conventions
- Docker multi-stage builds
- CI/CD optimization
Communication Protocol
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.
- 8d ago First seen · 277 lines · 38 tokens per session scan A 43c9d075601b
golang-pro is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,525 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
FAI Go Expert
Go development specialist — idiomatic Go 1.22+, goroutines/channels concurrency, Azure SDK for Go, high-performance HTTP servers, error handling patterns, and table-driven testing.
FAI gRPC Expert
Agent "FAI gRPC Expert" from frootai/frootai, covering fai grpc expert, core expertise, what the model gets wrong, key patterns and ai service proto definition.
FAI PHP Expert
PHP 8.3+ specialist — modern PHP with attributes, typed properties, enums, fibers, Composer PSR standards, Laravel/Symfony patterns, and PHP-based AI API integration.
go-expert
Go programming language strategist. Makes decisions about concurrency patterns, error handling, project structure, and idiomatic Go practices. Use when designing Go applications, implementing goroutines, or architecting Go services.
go-expert
../../skills/go-expert/agents/claude.md.
temporal-go
Go SDK specialist for Temporal.io (v1.36.0+). MUST BE USED for Go-specific Temporal development, workflow-safe primitives, context patterns, and determinism.