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/appkitnpx skills add vmkteam/claude-plugins --skill appkitgit 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 | $0.00061 | $0.00755 |
| Opus 5 | $0.00030 | $0.00378 |
| Sonnet 5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
appkit 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appkit
- Upstream: https://github.com/vmkteam/appkit
- Связанные: /embedlog, /cron, /prometheus (PromQL к
app_*метрикам)
Метрики (appkit/metrics)
metrics.Register(a.echo) — экспонирует /metrics.
Server: app_http_requests_total (labels: job, code, method, uri, server), app_http_responses_duration_seconds_*.
Client: app_http_client_requests_total, app_http_client_requests_inflight, app_http_client_responses_duration_seconds_* (labels: caller, origin).
Metadata: app_metadata_service (version, deps), app_metadata_services (sync/async/external links), app_metadata_db_connections_total, app_log_events_total.
Service Metadata (appkit/metadata)
Декларация зависимостей — используется /onboard и /investigate для auto-discovery топологии:
md := metadata.New(a.appName, version)
md.AddDatabase("postgres", a.db.PoolStats)
md.AddService("{dep_service}", metadata.Sync)
md.AddService("{async_service}", metadata.Async)
md.AddService("{ext_service}", metadata.External)
md.Register()
HTTP Client (appkit/httpclient)
Исходящие запросы с авто-метриками и internal headers:
client := httpclient.New(
httpclient.WithMetrics("caller-service"),
httpclient.WithInternalHeaders(appName, version),
)
Pprof (appkit/pprof)
pprof.Register(a.echo) → /debug/pprof/{,heap,goroutine,profile?seconds=30}.
X-Request-ID (appkit/xrid)
Генерация/валидация/прокидывание X-Request-ID. Обёртка для RPC handler: appkit.XRequestID(a.srv). В коде: xrid.FromContext(ctx).
VCS Version (appkit/vcs)
vcs.Version() — git commit hash из go build -ldflags или VCS info.
Real IP (appkit/realip)
a.echo.IPExtractor = realip.Extractor(trustedCIDRs) — учёт trust CIDR.
Route Listing
appkit.RegisterRouteList(a.echo) — HTML-список маршрутов на GET / (dev).
Context (appkit/appctx)
appctx.{IP, UserAgent, Platform, Version, Country}(ctx) — метаданные запроса.
Канонические handlers (echo)
func (a *App) registerHandlers() {
a.echo.Use(middleware.CORSWithConfig(middleware.CORSConfig{AllowOrigins: []string{"*"}}))
a.echo.GET("/status", a.statusHandler)
}
func (a *App) registerAPIHandlers() {
a.srv = rpc.New(a.db, a.Logger, a.cfg.Server.IsDevel)
a.echo.Any("/v1/rpc/*", echo.WrapHandler(appkit.XRequestID(a.srv)))
a.echo.GET("/v1/rpc/doc/*", echo.WrapHandler(smdbox.NewHandler(a.srv)))
}
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 · 83 lines · 61 tokens per session scan A c723dd30fabd
appkit is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 755 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…