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 skills add vmkteam/claude-plugins --skill prometheusgit clone --depth 1 https://github.com/vmkteam/claude-pluginsWrote 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/skills/vmkteam/claude-plugins/prometheus)<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/prometheus"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/prometheus/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/skills/vmkteam/claude-plugins/prometheus"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/prometheus.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 | $0.00054 | $0.01655 |
| Opus 5.5 | $0.00022 | $0.00662 |
| Sonnet 5.5 | $0.00011 | $0.00331 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
prometheus 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 23d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prometheus — метрики vmkteam-сервисов
Prometheus для метрик. Метрики из vmkteam/appkit, vmkteam/zenrpc, vmkteam/cron.
Конкретные хосты, job-имена определяются при онбординге.
Подключение
Profile: @{prom_profile}
Base URL: https://{prom_host}/api/v1
Также доступен через Grafana proxy (см. /grafana).
Метрики appkit (app_*)
HTTP (app_http_*)
| Метрика | Тип | Labels |
|---|---|---|
app_http_requests_total |
counter | job, code, method, uri, server |
app_http_responses_duration_seconds_count |
counter | job, code, method, uri, server |
app_http_responses_duration_seconds_sum |
counter | job, code, method, uri, server |
app_http_client_requests_total |
counter | job |
app_http_client_requests_inflight |
gauge | job |
RPC / zenrpc (app_rpc_*)
| Метрика | Тип | Labels |
|---|---|---|
app_rpc_responses_duration_seconds_count |
counter | job, code, method, platform, server, version |
app_rpc_responses_duration_seconds_sum |
counter | job, code, method, platform, server, version |
app_rpc_error_requests_total |
counter | job, code, method, platform, server, version |
Cron (app_cron_*)
| Метрика | Тип | Labels |
|---|---|---|
app_cron_active |
gauge | job |
app_cron_evaluated_total |
counter | job |
app_cron_evaluated_duration_seconds_* |
counter | job |
Прочие
| Метрика | Описание |
|---|---|
app_log_events_total |
Log events |
app_metadata_db_connections_total |
DB connections |
Labels
| Label | Описание |
|---|---|
job |
Сервис (определяется при онбординге) |
code |
HTTP/RPC status code |
method |
HTTP method или RPC method name (lowercase) |
uri |
HTTP URI |
platform |
Клиентская платформа (RPC) |
version |
Версия клиента (RPC) |
Команды pcurl
Instant query
# Общий формат (--data-urlencode обязателен для query с фигурными скобками)
pcurl @{profile} 'https://{host}/api/v1/query' -s -G --data-urlencode 'query={promql}'
# Health
pcurl @{profile} 'https://{host}/api/v1/query' -s -G --data-urlencode 'query=up{job="{service}"}'
# RPC RPS
pcurl @{profile} 'https://{host}/api/v1/query' -s -G --data-urlencode 'query=sum(rate(app_rpc_responses_duration_seconds_count{job="{service}"}[5m]))'
# RPC error rate
pcurl @{profile} 'https://{host}/api/v1/query' -s -G --data-urlencode 'query=sum(rate(app_rpc_error_requests_total{job="{service}"}[5m]))/sum(rate(app_rpc_responses_duration_seconds_count{job="{service}"}[5m]))'
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.
- 23d ago Changed · +1 lines b106804e260d
- 1mo ago First seen · 183 lines · 54 tokens per session scan A 05aa4357f654
prometheus is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 1,655 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…