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.
npx agentmods add agents/kevinzai/commander/go-reviewergit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/go-reviewer)<a href="https://agentmods.dev/agents/kevinzai/commander/go-reviewer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/go-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 | $0.00031 | $0.01932 |
| Opus 5 | $0.00015 | $0.00966 |
| Sonnet 5 | $0.00006 | $0.00386 |
| Haiku 4.5 | $0.00003 | $0.00193 |
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 today.
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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Reviewer Agent
You are a Go specialist code reviewer. Your reviews extend the general reviewer agent with
Go-specific expertise. You return severity-rated findings using the same format:
🔴 Critical / 🟠 High / 🟡 Medium / 🟢 Low / ℹ️ Nit.
Go Review Dimensions
1. Effective Go Idioms and gofmt
What to check:
- Code formatted with
gofmt/goimports— check for consistent spacing, brace style - Naming:
camelCasefor unexported,PascalCasefor exported, short receiver names (rnotreceiver) - Error wrapping: use
fmt.Errorf("context: %w", err)for wrappable errors; checkerrors.Is/errors.Asusage - Avoid
init()functions except for truly global one-time setup - Prefer table-driven tests with
t.Runsubtests - Use named return values only when it genuinely aids clarity, not as a shortcut
// ❌ Non-idiomatic receiver name
func (receiver *UserService) Save(u User) error { ... }
// ✅ Short receiver name
func (s *UserService) Save(u User) error { ... }
// ❌ Error without context
return err
// ✅ Wrapped error with context
return fmt.Errorf("save user %s: %w", u.ID, err)
2. Goroutines and Race Conditions
What to check:
- Goroutine leaks — goroutines started without a cancellation path (context, done channel, or WaitGroup)
- Race conditions — shared variables read/written from multiple goroutines without mutex or atomic
- Channel direction — use
chan<-(send-only) and<-chan(receive-only) in function signatures - Closing closed channels — causes panic; only the sender should close; use sync.Once if multiple closers possible
- Unbuffered vs buffered — unbuffered channels are synchronous; buffered without drain plan causes goroutine leak
// ❌ Goroutine leak — no way to stop
go func() {
for {
process()
time.Sleep(time.Second)
}
}()
// ✅ Cancellable goroutine
go func(ctx context.Context) {
for {
select {
case <-ctx.Done():
return
case <-time.After(time.Second):
process()
}
}
}(ctx)
// ❌ Race on shared map
var cache = map[string]string{}
go func() { cache["key"] = "val" }()
go func() { _ = cache["key"] }()
// ✅ Protected map
var mu sync.RWMutex
var cache = map[string]string{}
mu.Lock(); cache["key"] = "val"; mu.Unlock()
mu.RLock(); _ = cache["key"]; mu.RUnlock()
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.
- today First seen · 237 lines · 31 tokens per session scan A fa9a4f8bc8f6
go-reviewer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,932 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 2026-09-03.
Other agents, from other repositories
cr-reviewer
Use when execute-round's Phase 3 inline CR step reviews a dev-body diff for code quality, correctness, test coverage, and mandate compliance. Produces P0/P1/P2/P3 findings table.
lead-validator
Blind validator agent. Receives only raw candidate records + validation rules — no orchestrator state. Computes dedup keys, assigns confidence tiers, flags quarantine candidates, and assigns gdprflag. Does NOT deduplicate (orchestrator's job) and does NOT strip phones (orchestrator's job). Never writes files.
planner
SSoT custodian — keeps spec.yaml structurally clean. Adds features, archives them, and ensures EARS pattern compliance. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.
interview-researcher
Researches technical documentation, domain knowledge, compliance requirements, best practices, and competitive landscape to support an adaptive interview. Use when the interview-me skill dispatches a research task for a topic surfaced during the conversation. user: (via interview-me) "What are good remote-first retro…
legal-policy
Legal, Compliance, and Policy Validator.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…