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 skills/vmkteam/claude-plugins/securitynpx skills add vmkteam/claude-plugins --skill securitygit clone --depth 1 https://github.com/vmkteam/claude-pluginsWhat 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 | $0.00059 | $0.01401 |
| Opus 5 | $0.00030 | $0.00700 |
| Sonnet 5 | $0.00012 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
security 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security — безопасность vmkteam Go-сервисов
Справочник по безопасности для vmkteam-стека: JSON-RPC API, go-pg, zenrpc, auth middleware. Используется автоматически при code review (/go-review) и разработке (/solve).
Инструменты
| Инструмент | Что ищет | Команда |
|---|---|---|
gosec |
SQL injection, hardcoded credentials, weak crypto, command injection | gosec ./... |
govulncheck |
Уязвимости в зависимостях (только реально используемые функции) | govulncheck ./... |
gitleaks |
API keys, tokens, passwords в коде и git-истории | gitleaks detect --source . |
trivy |
Уязвимости в Docker-образах | CI only |
SQL Injection
Главная точка риска — _repo_ext.go (кастомные запросы).
Плохо — пользовательский ввод в raw SQL:
// УЯЗВИМО: searchText попадает в SQL напрямую
func (r OrderRepo) SearchOrders(ctx context.Context, searchText string) ([]Order, error) {
var orders []Order
_, err := r.db.Query(&orders,
"SELECT * FROM orders WHERE title LIKE '%"+searchText+"%'", nil)
return orders, err
}
Хорошо — параметризованный запрос через go-pg:
func (r OrderRepo) SearchOrders(ctx context.Context, searchText string) ([]Order, error) {
var orders []Order
err := r.db.Model(&orders).
Where("title ILIKE ?", "%"+searchText+"%").
Select()
return orders, err
}
Хорошо — если нужен raw SQL, использовать pg.SafeQuery:
q := r.db.Model(&orders)
q = q.Where("? ILIKE ?", pg.Ident("title"), "%"+searchText+"%")
Правило: go-pg ORM экранирует автоматически. Опасность только в Query() с конкатенацией строк.
Аутентификация и авторизация
Auth middleware (типичная ошибка — IDOR)
Middleware проверяет аутентификацию (есть ли валидный токен), но не авторизацию (может ли этот пользователь делать это действие).
Плохо — middleware пропустил, но метод не проверяет ownership:
func (s OrderService) GetByID(ctx context.Context, id int) (*Order, error) {
// Любой авторизованный пользователь может получить любой заказ
return s.repo.OrderByID(ctx, id)
}
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.
- 2d ago First seen · 146 lines · 59 tokens per session scan A 263e85a9cda7
security is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,401 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…