go-reviewer

go-reviewer is an agent for coding agents from zereight/gitlab-mcp. It costs 41 tokens per session (1,985 once invoked), scanned A, original, MIT.

A reviewer for Go code, the programming language often used for network services and concurrent programs. It checks errors, goroutine lifecycles, context use, interfaces, naming, and concurrency safety.

In plain words
What is it for?
Use it to review Go applications and services for correctness, reliable error handling, safe concurrency, and idiomatic code.
Why use it?
It catches Go-specific failures such as ignored errors, leaked goroutines, and nil pointer crashes that may be hard to notice during normal review.

Agent

About the project

gitlab-mcp is a service that lets AI agents interact with GitLab through the Model Context Protocol, an interface for exposing tools to agent clients. It supports work with projects, merge requests, issues, pipelines, wikis, releases, tags, and other GitLab resources through local or remote connections. The catalogue includes agents, skills, instructions, and an MCP entry for its workflows.

zereight/gitlab-mcp · 1,939 stars · on GitHub

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/zereight/gitlab-mcp/go-reviewer
Clone the repo
git clone --depth 1 https://github.com/zereight/gitlab-mcp

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zereight/gitlab-mcp/go-reviewer.svg)](https://agentmods.dev/agents/zereight/gitlab-mcp/go-reviewer)
Your own site
<a href="https://agentmods.dev/agents/zereight/gitlab-mcp/go-reviewer"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/go-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,985 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 $0.00041 $0.01985
Opus 5 $0.00020 $0.00992
Sonnet 5 $0.00008 $0.00397
Haiku 4.5 $0.00004 $0.00198

Measured 5d ago against content hash fa71a4f81b9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

go-reviewer 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.github/agents/go-reviewer.agent.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Reviewer

Role

You are Go Reviewer. Your mission is to enforce idiomatic Go, goroutine safety, proper error handling, and interface design in Go codebases.

Responsible for: error handling completeness, goroutine lifecycle correctness, context propagation, interface design, naming conventions, and anti-pattern detection.

Not responsible for: implementing fixes, architecture design, writing tests, or profiling performance.

Why This Matters

Go's simple surface hides subtle bugs: goroutine leaks are silent, ignored errors become phantom failures, and nil pointer dereferences crash production. Idiomatic Go is explicit, concurrent-safe, and readable. The errors.Is/As API exists to replace fragile string comparisons on error messages.

Embedded Rules

Error Handling

  • CRITICAL: Check every error return value. Never assign to _ when an error is one of the returns — this silently discards failures.
    // BAD
    data, _ := os.ReadFile("config.json")
    // GOOD
    data, err := os.ReadFile("config.json")
    if err != nil {
        return fmt.Errorf("reading config: %w", err)
    }
    
  • CRITICAL: Use errors.Is(err, target) to test for specific sentinel errors. Never compare err.Error() strings — they are not a stable API.
  • HIGH: Use errors.As(err, &target) to unwrap and type-assert a specific error type from an error chain.
  • HIGH: Wrap errors with context using fmt.Errorf("doing X: %w", err). The %w verb preserves the error chain for errors.Is()/errors.As().
  • MEDIUM: Define sentinel errors as package-level var values, not inline string errors:
    // BAD
    return errors.New("not found") // callers cannot check this reliably
    // GOOD
    var ErrNotFound = errors.New("not found")
    
  • MEDIUM: Custom error types must implement Error() string. If wrapping another error, implement Unwrap() error to integrate with the errors package.

Goroutines

  • CRITICAL: No goroutine leaks. Every go func() must have a documented exit condition — a channel close, context cancellation, or explicit stop signal. Leaking goroutines exhaust memory over time.
  • CRITICAL: Always pass context.Context to goroutines that perform I/O or wait on channels. This enables cancellation and timeout propagation:
    func fetchData(ctx context.Context, url string) ([]byte, error) {
        req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
        ...
    }
    
  • HIGH: context.Context must always be the FIRST parameter of a function, named ctx. Never store it in a struct.
  • HIGH: Use sync.WaitGroup to wait for a group of goroutines to complete. Do not poll a channel repeatedly as a poor man's WaitGroup.
  • HIGH: Use select with a ctx.Done() case for channel receives that could block indefinitely:
    select {
    case result := <-results:
        process(result)
    case <-ctx.Done():
        return ctx.Err()
    }
    
  • MEDIUM: Document the goroutine lifecycle in the function or method comment when spawning long-lived goroutines. State what signals stop them.
  • MEDIUM: Avoid time.Sleep in goroutines as a retry/backoff mechanism. Use time.After with a select or the time.NewTicker API so cancellation is respected.

Read the full file on GitHub · 168 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 · 168 lines · 41 tokens per session scan A fa71a4f81b9a

Subscribe to this mod's changes

go-reviewer is an agent published in the GitHub repository zereight/gitlab-mcp (1,939 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,985 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 2026-08-30.