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/lokinpx skills add vmkteam/claude-plugins --skill lokigit 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 | $0.00053 | $0.01604 |
| Opus 5 | $0.00026 | $0.00802 |
| Sonnet 5 | $0.00011 | $0.00321 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
loki 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loki — логи vmkteam-сервисов
Loki для логов. Доступен через Grafana datasource proxy. Структурированные JSON-логи из Go-сервисов (appkit).
Подключение
Profile: @{grafana_profile} (через datasource proxy)
Datasource UID: {loki_uid}
Два способа доступа:
| Способ | Base URL |
|---|---|
| UID-based (рекомендуется) | https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/ |
| Legacy ID-based | https://{grafana_host}/api/datasources/proxy/{loki_id}/loki/api/v1/ |
ВАЖНО: UID-based путь — /resources/query_range, /resources/labels (без /loki/api/v1/ префикса). Legacy — с /loki/api/v1/.
ВАЖНО: Stream labels vs JSON fields
Stream labels (можно использовать в {...} selector):
service_name— сервис_node— хост/нода_instance— UUID инстанса_version— версия деплоя
JSON fields (доступны ТОЛЬКО через | json | field=value):
level— INFO, ERROR, WARNmethod— RPC методplatform— desktop, iOS, android, mobiledurationMS— длительность в ms (число)err— текст ошибки (<nil>если нет)msg— тип записи (rpc, http, etc.)ip,country,version,userAgent
НЕ ИСПОЛЬЗУЙ level, method, platform в {...} selector — только через | json |.
Правильно: {service_name="{service}"} | json | level="ERROR"
Неправильно: {service_name="{service}",level="ERROR"}
Формат лог-записи (appkit JSON)
{
"time": "2026-04-03T12:00:28.995Z",
"level": "INFO",
"msg": "rpc",
"method": "lists.episodesunwatched",
"duration": "116.582386ms",
"durationMS": 116,
"err": "<nil>",
"platform": "desktop",
"ip": "128.65.1.139"
}
Команды pcurl
Поиск логов (UID-based)
# Логи сервиса за 5 минут
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"}' \
--data-urlencode "start=$(date -v-5M +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
# Только ошибки
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"} | json | level="ERROR"' \
--data-urlencode "start=$(date -v-1H +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
# По RPC методу
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"} | json | method="{rpc_method}"' \
--data-urlencode "start=$(date -v-1H +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
# Медленные запросы (>500ms)
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"} | json | durationMS > 500' \
--data-urlencode "start=$(date -v-1H +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
# По тексту (line filter — быстрее)
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"} |~ "{search_text}"' \
--data-urlencode "start=$(date -v-1H +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
# Ошибки с текстом err (исключая <nil>)
pcurl @{profile} "https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/query_range" -s -G \
--data-urlencode 'query={service_name="{service}"} | json | err!="<nil>"' \
--data-urlencode "start=$(date -v-1H +%s)000000000" \
--data-urlencode "end=$(date +%s)000000000" \
--data-urlencode 'limit=50'
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 · 145 lines · 53 tokens per session scan A d96c47c85080
loki is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,604 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.
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…
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.