go-review-service

go-review-service is a skill for Claude Code from JotJunior/cstk. It costs 17 tokens per session (3,092 once invoked), scanned A, original, MIT.

A read-only checker for Go microservices, which are independently deployable parts of a larger application.

In plain words
What is it for?
Use it to audit a named Go service and report passing, failing, warning, or irrelevant checks with file and line references.
Why use it?
It finds violations of the project's coding and service conventions before they cause maintenance or integration problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument.

Part of the cstk-language-go plugin — 7 skills shipped together

Good fit Use it to audit a named Go service and report passing, failing, warning, or irrelevant checks with file and line references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jotjunior/cstk/go-review-service
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.

Any agent
npx skills add JotJunior/cstk --skill go-review-service
Clone the repo
git clone --depth 1 https://github.com/JotJunior/cstk

Made for: Claude Code.

Or install cstk-language-go, the plugin that ships this one along with the rest of its 7 skills.

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-review-service

README.md
[![agentmods](https://agentmods.dev/badge/skills/jotjunior/cstk/go-review-service/github.svg)](https://agentmods.dev/skills/jotjunior/cstk/go-review-service)
Your own site
<a href="https://agentmods.dev/skills/jotjunior/cstk/go-review-service"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/go-review-service/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.

agentmods 80×15 button for go-review-service

Your own site · 80×15
<a href="https://agentmods.dev/skills/jotjunior/cstk/go-review-service"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/go-review-service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,092 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.03092
Opus 5 $0.00009 $0.01546
Sonnet 5 $0.00003 $0.00618
Haiku 4.5 $0.00002 $0.00309

Measured 11d ago against content hash 2c80d643f6e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

go-review-service 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 11d 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/cstk-language-go/skills/go-review-service/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Review Service

Perform a comprehensive read-only audit of a GOB Go microservice, checking 17 conventions. Outputs a structured PASS/FAIL/WARNING report with line references.

Trigger Phrases

"review service", "audit service", "validar servico", "check service", "verificar servico", "checar servico"

Arguments

$ARGUMENTS should specify:

  • Service name (e.g., gob-member-service) — required
  • Focus area (optional) — e.g., "middleware", "routes", "repository" to narrow the audit

Pre-Flight

Determine the service root:

services/{service-name}/

Read these files first (in parallel where possible):

  1. cmd/api/main.go — middleware order, wiring, shutdown
  2. internal/factory/factory.go — repository factory
  3. internal/repository/repository.go — interfaces
  4. internal/handler/*.go — route registration
  5. go.mod — module path, dependencies
  6. migrations/ — list files for schema reference

Checks (17 total)

For each check, output one of:

  • PASS — convention followed correctly
  • FAIL — convention violated (include file:line reference and what's wrong)
  • WARNING — partially followed or uncertain (include details)
  • N/A — not applicable to this service

Check 1: Middleware Order in main.go

Expected order (top to bottom in main.go):

  1. recover.New()
  2. requestid.New()
  3. apmfiber.Middleware(apmfiber.WithTracer(tracer)) — after requestid, before logging (unconditional/nil-safe; rollout-window dual-accept detailed in Check 3)
  4. middleware.LoggingWithLogger(log) or middleware.Logging()
  5. cors.New(...) — with AllowOrigins, AllowHeaders, AllowMethods, AllowCredentials
  6. middleware.DryRun(...) — if service supports dry-run
  7. middleware.DryRunFinalizer() — if dry-run present
  8. middleware.AuditPublisher(...) — after cors/dryrun, before endpoints

Search: Look for app.Use( calls in main.go. Verify order matches.

Check 2: Audit Middleware

  • Separate RabbitMQ connection (rabbitmq.NewFromURL)
  • Uses middleware.AuditExchange constant
  • Non-blocking: wrapped in if rmqURL != "" with warning on failure
  • Placed AFTER cors and BEFORE health/ready/version endpoints
  • defer auditRMQ.Close() present

Read the full file on GitHub · 302 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. 11d ago First seen · 302 lines · 17 tokens per session scan A 2c80d643f6e4

Subscribe to this mod's changes

go-review-service is a skill published in the GitHub repository JotJunior/cstk (23 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 3,092 once invoked, about $0.0001 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.