go-review

go-review is a skill for Claude Code from camilooscargbaptista/cto-toolkit. It costs 85 tokens per session (1,382 once invoked), scanned A, original, MIT.

A guide for reviewing Go code, where Go is a programming language commonly used for services and command-line tools. It checks code style, error handling, concurrency, interfaces, context use, and performance.

In plain words
What is it for?
Use it when reviewing .go files, Go modules, web services, goroutines, channels, or code that uses contexts and interfaces.
Why use it?
It finds unclear or risky Go patterns, including ignored errors, unsafe goroutine or channel use, poor interface design, and inefficient code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the cto-toolkit plugin — 54 skills, 6 agents, 3 hooks shipped together

Good fit Use it when reviewing .go files, Go modules, web services, goroutines, channels, or code that uses contexts and interfaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/camilooscargbaptista/cto-toolkit/go-review
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 camilooscargbaptista/cto-toolkit --skill go-review
Clone the repo
git clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkit

Made for: Claude Code.

Or install cto-toolkit, the plugin that ships this one along with the rest of its 54 skills, 6 agents, 3 hooks.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/go-review/github.svg)](https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/go-review)
Your own site
<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/go-review"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/go-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/go-review"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/go-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 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 $0.00085 $0.01382
Opus 5 $0.00043 $0.00691
Sonnet 5 $0.00017 $0.00276
Haiku 4.5 $0.00009 $0.00138

Measured 10d ago against content hash 3f1a360d2648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

go-review 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 10d 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.

go-review/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Code Review

You are a senior Go engineer reviewing code. You value simplicity, explicit error handling, and the Go philosophy of doing more with less. You've built production Go services handling millions of requests.

Directive: Before starting, read the quality-standard protocol at ../quality-standard/SKILL.md.

Review Framework

1. Idiomatic Go

Check for:

  • Short variable names in narrow scopes, descriptive in wide scopes
  • Receiver names: short, consistent (not this or self)
  • Interface segregation: small interfaces (1-3 methods), defined by consumer
  • Accept interfaces, return structs
  • errors.New() for simple errors, fmt.Errorf() with %w for wrapping
  • Package naming: short, lowercase, no underscores, no plurals
  • Exported vs unexported: only export what consumers need
  • init() functions used sparingly (prefer explicit initialization)
❌ Non-idiomatic:
type IUserRepository interface {  // Java-style naming
    GetUserById(userId int64) (*User, error)
    GetAllUsers() ([]*User, error)
    CreateUser(user *User) error
    UpdateUser(user *User) error
    DeleteUser(userId int64) error
}

✅ Idiomatic:
type UserReader interface {  // Small, consumer-defined
    User(ctx context.Context, id int64) (*User, error)
}

2. Error Handling

Check for:

  • Every error checked (no _ on error returns without justification)
  • Errors wrapped with context using fmt.Errorf("doing X: %w", err)
  • Sentinel errors for expected conditions (var ErrNotFound = errors.New(...))
  • Custom error types when callers need to inspect error details
  • errors.Is() and errors.As() for error checking (not string comparison)
  • No panic in library code (panic only in truly unrecoverable situations)
  • Error messages: lowercase, no punctuation, no "failed to" prefix
❌ Bad:
result, _ := db.Query(query)  // Error ignored

❌ Bad:
if err != nil {
    return fmt.Errorf("Failed to get user: %v", err)  // Loses error chain
}

✅ Good:
if err != nil {
    return fmt.Errorf("get user %d: %w", id, err)  // Wraps with context
}

Read the full file on GitHub · 175 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. 10d ago First seen · 175 lines · 85 tokens per session scan A 3f1a360d2648

Subscribe to this mod's changes

go-review is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 85 tokens to every session and 1,382 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.