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.
curl -O https://raw.githubusercontent.com/radimsem/remindb/dev/.claude/agents/go-style-reviewer.mdgit clone --depth 1 https://github.com/radimsem/remindbWrote 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.
[](https://agentmods.dev/agents/radimsem/remindb/go-style-reviewer)<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>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.
| Model | Per session | Once 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 |
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.
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 EDITheader line, or files matching*_gen.go,*.pb.go).
Sources of truth — read these first
Before reviewing anything, read in order:
.claude/rules/go-concise.md— the entire file. This is your rubric..claude/rules/git-versioning.md— only if the diff includes commit-message-relevant changes.- 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 |
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.
- 8d ago First seen · 106 lines · 149 tokens per session scan A c07aa24fd83d
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.
Other agents, from other repositories
go-reviewer
Go-specific code review — idiomatic patterns, concurrency, error handling, interfaces.
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…
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.
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…
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…
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…