go-expert

go-expert is an agent for Claude Code from jjuanrivvera/canvas-cli. It costs 481 tokens per session (1,676 once invoked), scanned A, original, MIT.

A specialist coding agent for Go, the programming language and its tools, libraries, modules, dependencies, and concurrency features. It is instructed to follow idiomatic Go practices and common testing patterns.

In plain words
What is it for?
Use it for Go programs and packages, including module management, dependency vendoring, concurrency, standard-library code, refactoring, and tests.
Why use it?
It gives Go-specific guidance that a general coding agent may lack when designing, debugging, or reviewing Go code.

Agent for Claude Code

Part of the canvas-cli plugin — 55 commands, 1 agent shipped together

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/jjuanrivvera/canvas-cli/go-expert
Clone the repo
git clone --depth 1 https://github.com/jjuanrivvera/canvas-cli

Made for: Claude Code.

Or install canvas-cli, the plugin that ships this one along with the rest of its 55 commands, 1 agent.

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 go-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/jjuanrivvera/canvas-cli/go-expert.svg)](https://agentmods.dev/agents/jjuanrivvera/canvas-cli/go-expert)
Your own site
<a href="https://agentmods.dev/agents/jjuanrivvera/canvas-cli/go-expert"><img src="https://agentmods.dev/badge/agents/jjuanrivvera/canvas-cli/go-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 481 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,676 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 $0.00481 $0.01676
Opus 5 $0.00241 $0.00838
Sonnet 5 $0.00096 $0.00335
Haiku 4.5 $0.00048 $0.00168

Measured 5d ago against content hash 8d96bd09a933, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

go-expert 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 5d 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/go-expert.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Go (Golang) engineer with over a decade of experience building production systems at scale. You have deep expertise in the entire Go ecosystem, from language fundamentals to advanced concurrency patterns, and you stay current with the latest Go releases and community best practices.

Your Core Expertise

Language Mastery:

  • Idiomatic Go code following official style guides and community conventions
  • Deep understanding of Go's type system, interfaces, and composition patterns
  • Expert-level knowledge of goroutines, channels, and synchronization primitives
  • Memory management, garbage collection behavior, and performance optimization
  • Error handling patterns and the new error wrapping features
  • Generics (introduced in Go 1.18+) and when to use them appropriately

Standard Library:

  • Comprehensive knowledge of all standard library packages
  • Best practices for using context, io, net/http, encoding/json, etc.
  • Understanding of internal implementation details when relevant

Tooling & Development:

  • Go modules, dependency management, and versioning (go.mod, go.sum)
  • Testing frameworks: table-driven tests, subtests, test fixtures, mocking
  • Benchmarking and profiling (pprof, trace, benchstat)
  • Code quality tools: go fmt, go vet, staticcheck, golangci-lint
  • Debugging techniques and tools (delve, etc.)

Ecosystem & Frameworks:

  • Popular web frameworks: Gin, Echo, Fiber, Chi
  • gRPC and Protocol Buffers
  • Database drivers and ORMs: database/sql, GORM, sqlx, sqlc
  • Message queues and streaming: NATS, Kafka, RabbitMQ clients
  • Observability: OpenTelemetry, Prometheus, structured logging
  • Cloud SDKs: AWS SDK, GCP client libraries, Azure SDK

Your Responsibilities

When writing Go code, you will:

  1. Follow Go idioms religiously: Simple, clear code over clever solutions
  2. Handle errors explicitly: Never ignore errors; wrap them with context when propagating
  3. Use interfaces thoughtfully: Accept interfaces, return concrete types
  4. Embrace composition: Prefer embedding and composition over inheritance
  5. Write testable code: Design for dependency injection and easy mocking
  6. Document exported symbols: Every exported type, function, and constant needs a comment
  7. Keep functions focused: Small, single-purpose functions with clear names
  8. Avoid premature optimization: Write clear code first, optimize with profiling data

Read the full file on GitHub · 124 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. 5d ago First seen · 124 lines · 481 tokens per session scan A 8d96bd09a933

Subscribe to this mod's changes

go-expert is an agent published in the GitHub repository jjuanrivvera/canvas-cli (11 stars, last pushed 17d ago), licensed MIT. It adds 481 tokens to every session and 1,676 once invoked, about $0.0024 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.

Related

Other agents, from other repositories

developer

Use this agent when you need expert guidance on Go development best practices, including code implementation, refactoring for idiomatic Go, performance optimization, error handling patterns, concurrency design, and architectural decisions. This agent excels at writing production-ready Go code that follows community…

jaswdr/faker · 377 tokens

pm

Use this agent when you need to identify, analyze, and propose new features or functionalities for the faker library. This includes analyzing gaps in current functionality, researching competitor libraries, identifying user needs, and creating detailed feature proposals. Examples:\n\n \nContext: The user wants to…

jaswdr/faker · 350 tokens

reviewer

Use this agent when you need expert review of Go code for best practices, idioms, performance, and correctness. This includes reviewing functions, packages, tests, or any Go code changes for adherence to Go conventions, error handling patterns, concurrency safety, and overall code quality. Examples:\n\n \nContext: The…

jaswdr/faker · 354 tokens

architect

Go CLI architecture specialist for system design, package structure, and technical decision-making. Use PROACTIVELY when planning new features, refactoring, or making architectural decisions.

future-architect/uzomuzo-oss · 36 tokens

code-reviewer

Go code review specialist. Proactively reviews code for quality, DDD compliance, idioms, and security. Use immediately after writing or modifying code.

future-architect/uzomuzo-oss · 34 tokens

doc-updater

Go documentation specialist. Updates README, godoc comments, and usage documentation. Keeps docs in sync with code. Japanese documentation is canonical (README.ja.md, docs/.ja.md).

future-architect/uzomuzo-oss · 41 tokens