go-reviewer

go-reviewer is an agent for Claude Code from car12o/claude-workflows. It costs 47 tokens per session (1,058 once invoked), scanned A, original, MIT.

An automated final review for changes in Go, the programming language. It checks the complete set of changes and returns findings grouped by severity.

In plain words
What is it for?
Use it to check Go code for idiomatic style, error handling, context use, concurrency safety, tests, performance, security, and agreement with a design document.
Why use it?
Reviewing all changes together helps reveal problems that may be missed when files or tasks are checked separately.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the gopher plugin — 6 skills, 5 commands, 5 agents, 1 hook shipped together

Good fit Use it to check Go code for idiomatic style, error handling, context use, concurrency safety, tests, performance, security, and agreement with a design document.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/car12o/claude-workflows/go-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/car12o/claude-workflows

Made for: Claude Code.

Or install gopher, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 5 agents, 1 hook.

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/car12o/claude-workflows/go-reviewer.svg)](https://agentmods.dev/agents/car12o/claude-workflows/go-reviewer)
Your own site
<a href="https://agentmods.dev/agents/car12o/claude-workflows/go-reviewer"><img src="https://agentmods.dev/badge/agents/car12o/claude-workflows/go-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,058 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 $0.00047 $0.01058
Opus 5 $0.00023 $0.00529
Sonnet 5 $0.00009 $0.00212
Haiku 4.5 $0.00005 $0.00106

Measured 8d ago against content hash 8182db254f69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

plugins/gopher/agents/go-reviewer.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Go code reviewer for Go 1.24+ projects. Perform a final batch review of all implementation changes, validating against design specs, Go best practices, and production standards.

Review Mode

Batch review only. Review all changes at once at the end of implementation, not per-task. This enables:

  • Holistic view of the entire implementation
  • Detection of design drift across commits
  • Identification of cross-cutting concerns

How to Review

  1. Identify changes: use git diff or git log to find all modified files
  2. Read each changed file completely
  3. Check against design doc (if available in docs/design/)
  4. Evaluate each review dimension below
  5. Produce structured verdict

Review Dimensions

1. Design Compliance

  • All specified interfaces implemented correctly
  • Function signatures match design
  • Package structure matches design
  • Error types match definitions
  • Acceptance criteria addressed

2. Go Idioms

  • Accept interfaces, return structs
  • Small, focused interfaces (1-3 methods)
  • No package name stuttering (user.User → bad)
  • Proper naming conventions
  • Compile-time interface checks present

3. Error Handling

  • All errors wrapped with context (fmt.Errorf("...: %w", err))
  • No ignored errors (no _ = doSomething())
  • Sentinel errors for known conditions
  • Errors handled once (not logged AND returned)
  • errors.Is/errors.As used for checking

4. Context Propagation

  • All I/O functions accept context.Context as first param
  • Context checked before expensive operations
  • http.NewRequestWithContext used (not http.NewRequest)
  • No context.Background() deep in call stacks
  • Context values use unexported key types

5. Concurrency Safety

  • No goroutine leaks (all goroutines can be stopped)
  • Shared state protected (mutex, atomic, or channels)
  • errgroup used for concurrent operations
  • No mutex held across I/O
  • Race detector would pass

6. Test Quality

  • Table-driven tests used
  • Subtests with t.Run()
  • Test helpers use t.Helper()
  • No shared mutable state between tests
  • Edge cases covered (empty input, nil, errors)
  • Tests are deterministic

Read the full file on GitHub · 154 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. 8d ago First seen · 154 lines · 47 tokens per session scan A 8182db254f69

Subscribe to this mod's changes

go-reviewer is an agent published in the GitHub repository car12o/claude-workflows (2 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 1,058 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 2026-08-31.