go-expert

go-expert is a skill for Claude Code from Miaoge-Ge/coding-agent-skills. It costs 83 tokens per session (1,090 once invoked), scanned A, original, MIT.

A set of guidance for writing and refactoring Go, a programming language known for built-in support for concurrent work. It covers errors, interfaces, the standard library, and coordination between goroutines, which are lightweight concurrent tasks.

In plain words
What is it for?
Use it when building Go packages, designing concurrent code, fixing race or context issues, or choosing standard-library and package-layout approaches.
Why use it?
It helps avoid common Go problems such as ignored errors, data races, deadlocks, leaked goroutines, and unclear interfaces.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the go-expert plugin — 1 skill shipped together

Good fit Use it when building Go packages, designing concurrent code, fixing race or context issues, or choosing standard-library and package-layout approaches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/miaoge-ge/coding-agent-skills/go-expert
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.

Any agent
npx skills add Miaoge-Ge/coding-agent-skills --skill go-expert
Clone the repo
git clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skills

Made for: Claude Code.

Or install go-expert, the plugin that ships this one along with the rest of its 1 skill.

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/skills/miaoge-ge/coding-agent-skills/go-expert/github.svg)](https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/go-expert)
Your own site
<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/go-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/go-expert/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 go-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/go-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/go-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,090 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 $0.00083 $0.01090
Opus 5 $0.00042 $0.00545
Sonnet 5 $0.00017 $0.00218
Haiku 4.5 $0.00008 $0.00109

Measured 9d ago against content hash 6e66b1b6b456, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

plugins/go-expert/skills/go-expert/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Expert

Clear is better than clever. Handle every error explicitly, make the zero value useful, and give every goroutine an owner and an exit. "Share memory by communicating," but a Mutex is fine for protecting state.

When to Use

  • Writing or refactoring Go.
  • Designing concurrent code (goroutines, channels, context, select).
  • Data races, deadlocks, goroutine leaks, or context propagation bugs.
  • Package layout, interfaces, and standard-library usage.

When NOT to Use

  • Other languages → the relevant language skill.
  • System-level architecture → software-architect.

Core Principles

1. Errors are explicit values

  • Check immediately: if err != nil { return fmt.Errorf("doing X: %w", err) }. Wrap with %w to preserve the chain; inspect with errors.Is (sentinel) / errors.As (typed).
  • Add context at each layer ("opening config: …") but don't double-log the same error. Return errors up; log once at the boundary.
  • Panic only for truly unrecoverable programmer errors, never for normal control flow.

2. Interfaces & types

  • Accept interfaces, return concrete types. Keep interfaces small (often one method) and define them in the consumer package, not the producer.
  • Make the zero value useful (sync.Mutex, bytes.Buffer work unboxed). Use defer for cleanup (close/unlock) right after acquisition.

3. Concurrency with ownership

  • Every goroutine needs a clear lifetime and exit path — leaks are silent. Use sync.WaitGroup or errgroup to wait, and bound concurrency (errgroup.SetLimit, worker pool, semaphore).
  • context.Context is the first parameter for anything cancelable/IO-bound; honor ctx.Done(). Never store a Context in a struct.
  • Channels for handoff/signaling; Mutex for protecting shared state. Close a channel from the sender, once. Prefer select with ctx for cancelable waits.

4. Tooling & structure

  • gofmt (non-negotiable), go vet, golangci-lint. Always test concurrent code with -race.
  • Organize by capability; keep private code under internal/. Avoid premature interfaces and needless abstraction.

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 83 tokens per session scan A 6e66b1b6b456

Subscribe to this mod's changes

go-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,090 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 2026-08-31.