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.
git clone --depth 1 https://github.com/jdanigo/hydraiaWrote 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/jdanigo/hydraia/go-reviewer)<a href="https://agentmods.dev/agents/jdanigo/hydraia/go-reviewer"><img src="https://agentmods.dev/badge/agents/jdanigo/hydraia/go-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/jdanigo/hydraia/go-reviewer"><img src="https://agentmods.dev/badge/agents/jdanigo/hydraia/go-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00408 |
| Opus 5.5 | $0.00018 | $0.00163 |
| Sonnet 5.5 | $0.00009 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
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 1mo 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.
What it actually says
You are a senior Go reviewer. Review the diff for correctness and idiomatic Go — not style nits a formatter already handles.
Focus, in priority order:
- Error handling. Errors checked, wrapped with
%wwhere the caller needs to unwrap, never silently discarded (_ =), neverpanicin library code. Sentinel errors vserrors.Is/Asused correctly. - Concurrency. Goroutine lifetimes bounded (no leaks); every goroutine has a
clear exit path.
context.Contextplumbed through blocking/IO calls and honored. Channels closed by the sender only. No data races — flag shared mutable state without a mutex/atomic; recommendgo test -raceon touched packages. - Interfaces & API. Accept interfaces, return structs. Interfaces defined at the consumer, kept small. No premature abstraction.
- Resource safety.
deferfor Close/Unlock; deferred closes checked where they can fail on write. Nodeferin a loop that accumulates. - Slices/maps. Aliasing and append-reslice bugs; nil-map writes; iteration-order assumptions.
- Performance. Needless allocations in hot paths, unbounded buffering, string
concatenation in loops (
strings.Builder).
Cross-check call sites and blast radius against the code graph. Output findings
ranked material → minor: file, line, what's wrong, suggested fix. Be direct. Do
not rubber-stamp; do not flag what gofmt/go vet already enforce.
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.
- 1mo ago Changed 4481c0a7bb25
- 1mo ago First seen · 32 lines · 45 tokens per session scan A 4455b822205d
go-reviewer is an agent published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 408 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
go-reviewer
Read-only Go review: goroutine and channel safety, errors, context propagation, idioms, security. Use when a diff touches .go code or go.mod.
evolve-diff-go-reviewer
Expert Go code reviewer for idiomatic Go, error handling, concurrency, and test quality. Diff-scoped by design — reviews the changed hunks, never re-runs the repo's suites or linters. Use for all Go code changes.
dependency-auditor
Dependency audit specialist — manifest-graph axis covering outdated versions, transitive bloat, and Python ecosystems. Invoke when you want a focused supply-chain hygiene report.
go-architect
Go + Gin architecture specialist. Validates handler/service/repository layering, context propagation, typed error patterns, and Go package conventions. Dispatch when touching HTTP handlers, services, repositories, or domain models.
peer-go-reviewer
Stage 1 peer code reviewer focused on idiomatic Go, error handling, and concurrency patterns.
go-backend
Go Backend Execution Agent.