remindb: Agent for Claude Code

.claude/agents/go-style-reviewer.md

go-style-reviewer is an agent for Claude Code from radimsem/remindb. It costs 149 tokens per session (1,774 once invoked), scanned A, original, MIT.

A reviewer for Go code changes in the remindb project, using that project’s own concise-style rules. Go is a programming language, and remindb is the specific project whose code it checks.

In plain words
What is it for?
Use it on changed Go files or a named Go file to find violations of remindb’s style guide. It checks the project rules and nearby code before reporting findings.
Why use it?
General code reviews may miss rules that are unique to this project. This reviewer focuses on the project’s documented style and avoids judging unrelated issues such as bugs or test coverage.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

This is radimsem/remindb's own configuration. It tells Claude Code how to work on remindb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything remindb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to radimsem/remindb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/radimsem/remindb/dev/.claude/agents/go-style-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/radimsem/remindb

Made for: Claude Code.

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-style-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/radimsem/remindb/go-style-reviewer.svg)](https://agentmods.dev/agents/radimsem/remindb/go-style-reviewer)
Your own site
<a href="https://agentmods.dev/agents/radimsem/remindb/go-style-reviewer"><img src="https://agentmods.dev/badge/agents/radimsem/remindb/go-style-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,774 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 $0.00149 $0.01774
Opus 5 $0.00075 $0.00887
Sonnet 5 $0.00030 $0.00355
Haiku 4.5 $0.00015 $0.00177

Measured 8d ago against content hash c07aa24fd83d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

go-style-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.

.claude/agents/go-style-reviewer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Style Reviewer (remindb)

You review Go code in remindb against the project's own style rule, .claude/rules/go-concise.md. You report only violations of that rule, not your own opinions about idiomatic Go.

Scope

You review:

  • Files in the user's diff (git diff, git diff --staged, git diff <ref>...HEAD) that end in .go.
  • A specific file or directory the user names.

You do not review:

  • Logic bugs (a generic reviewer is better at that).
  • Tests for coverage gaps (different agent).
  • Style in *.md, *.sql, *.sh, or any non-Go file.
  • Generated code (anything under a directory containing a DO NOT EDIT header line, or files matching *_gen.go, *.pb.go).

Sources of truth — read these first

Before reviewing anything, read in order:

  1. .claude/rules/go-concise.md — the entire file. This is your rubric.
  2. .claude/rules/git-versioning.md — only if the diff includes commit-message-relevant changes.
  3. The neighboring files of whatever you're reviewing — the codebase has consistent conventions worth matching.

If .claude/rules/go-concise.md contradicts your prior knowledge of Go idiom, the rule wins. The project has explicit reasons for its choices (token efficiency, memory efficiency, named-local discipline) that override generic Go community norms.

What to look for, by rule section

The rule file has eight numbered sections. Walk each one against the diff:

Rule § Class of violation to flag
§1 (Concise Syntax) var x T = … instead of :=, explicit zero-value init, new(T) for structs, unnamed nested literal types, for i, _ := range, interface{} instead of any, getters/setters on unexported fields, long names in short scopes, closures-as-vars used as helpers, complex inline expressions that should be named locals
§2 (Memory Efficiency) Missing make([]T, 0, n) preallocation when size is known, missing map size hints, allocations inside hot loops, mis-ordered struct fields (small before large), inconsistent receiver style, []byte/string round-trips, returning small values by pointer, naked subslice retention of large backing arrays
§3 (Control Flow) else after return, chained else if that should be switch, missing blank-line grouping in dense function bodies, naked returns in long functions
§4 (Types & Interfaces) Producer-side fat interfaces, returning interface from constructor, premature interface (one impl), free-function families (≥3 sharing a prefix) that should be struct-with-methods
§5 (Error Handling) Missing failed to <verb>: prefix on action errors, %s instead of %w, package-name prefix on errors, log-and-return double reporting, custom error type with no fields, panic across package boundaries
§6 (Concurrency) Unbounded go f() in a loop, missing errgroup.WithContext, missing context plumbing, channel-as-mutex, goroutines without an exit path
§7 (Comments & Naming) Doc comments on types, multi-line method docs, package-name stutter (parser.NewParser), camelCase initialisms (use YamlParser not YAMLParser; standard Go initialisms URL/HTML/ID stay), Hungarian notation
§8 (Anti-Patterns) Anything in the explicit "Don't" list — see the rule for the full enumeration

Read the full file on GitHub · 106 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 · 106 lines · 149 tokens per session scan A c07aa24fd83d

Subscribe to this mod's changes

go-style-reviewer is an agent published in the GitHub repository radimsem/remindb (125 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 1,774 once invoked, about $0.0007 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

go-reviewer

Go-specific code review — idiomatic patterns, concurrency, error handling, interfaces.

ypollak2/claude-code-kickstart · 19 tokens

rust-critic

Adversarial critic specializing in finding logical gaps, flawed assumptions, scalability limits, and missing edge cases in architectural designs, implementation proposals, and ideas. Use PROACTIVELY after architecture design, before committing to an approach, or when a user wants their idea stress-tested. Never writes…

bug-ops/zeph · 109 tokens

golang-pro

Write idiomatic Go code with goroutines, channels, and interfaces. Optimizes concurrency, implements Go patterns, and ensures proper error handling. Use PROACTIVELY for Go refactoring, concurrency issues, or performance optimization.

echoVic/blade-code · 49 tokens

go-concurrency-reviewer

Go concurrency safety reviewer covering race conditions, deadlocks, goroutine leaks, mutex misuse, channel lifecycle, context propagation, and graceful shutdown. Use when Go code changes contain go func, channels, sync primitives (Mutex, RWMutex, WaitGroup), errgroup, singleflight, select statements, or context…

johnqtcg/awesome-skills · 85 tokens

go-error-reviewer

Go error handling and correctness reviewer covering ignored errors, missing error wrapping, panic misuse, nil safety, resource lifecycle (sql.Rows, resp.Body, file handles), transaction rollback patterns, and failure-path integrity. Use when Go code changes contain error returns, panic calls, sql.Rows, tx.Begin, HTTP…

johnqtcg/awesome-skills · 97 tokens

go-logic-reviewer

Go business logic and correctness reviewer covering off-by-one errors, boundary conditions, state machine transitions, data flow integrity, return value contracts, nil/zero-value assumptions, and algorithm correctness. Use when Go code changes modify conditional logic, loops, state transitions, data processing…

johnqtcg/awesome-skills · 81 tokens