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 skills-checkgit 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/skills-check)<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/skills-check"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/skills-check/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/skills-check"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/skills-check.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 | $0.00040 | $0.01179 |
| Opus 5.5 | $0.00016 | $0.00472 |
| Sonnet 5.5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
skills-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skills-check — smoke-тесты интеграций
Быстрая проверка, что внешние системы из project-index.md (auto-memory проекта) и ~/.claude/memory/infra-{group}.md отвечают на канонические запросы data-source скиллов. Нужна, когда URL или API провайдеров могли измениться, токены истечь или профили pcurl разойтись с конвенциями скиллов.
Использование
/skills-check # все настроенные интеграции
/skills-check youtrack gitlab # только перечисленные
/skills-check --verbose # плюс проверка формы ответа
Пробы
| Секция | Проба (GET) | Заголовок | check для --verbose |
|---|---|---|---|
| YouTrack | https://{yt_host}/api/admin/projects?fields=id&$top=1 |
- |
type == "array" |
| GitLab | https://{gl_host}/api/v4/projects/{gl_project_id}?simple=true |
- |
.id != null |
| Sentry | https://{sentry_host}/api/0/organizations/{org}/projects/?per_page=1 |
- |
type == "array" |
| Grafana | https://{grafana_host}/api/datasources |
- |
type == "array" |
| Prometheus (Grafana proxy) | https://{grafana_host}/api/datasources/uid/{prom_uid}/resources/api/v1/labels |
- |
.status == "success" |
| Loki (Grafana proxy) | https://{grafana_host}/api/datasources/uid/{loki_uid}/resources/labels |
- |
.status == "success" |
| Kibana / OpenSearch | https://{kibana_host}/api/status |
osd-xsrf: true |
- |
| Nomad | https://{nomad_host}/v1/status/leader |
- |
- |
| API dev/prod | https://{api_host}/{rpc_endpoint}?smd |
- |
.services != null |
check нужен, потому что прокси или SSO могут вернуть HTTP 200 со страницей логина вместо JSON.
Порядок
- Прочитай
project-index.mdи infra-файл. Если project-index нет — предложи пользователю запустить/onboardи остановись. - Собери строки
name<TAB>profile<TAB>url<TAB>header<TAB>checkпо таблице для настроенных секций (или только перечисленных в аргументах). Секции, которых нет в project-index, в таблицу попадут какSKIP. - Передай строки скрипту (с
--verbose, если он указан) — он сам проверит профили поpcurl show, выполнит GET параллельно (до 6 одновременно), в--verboseпроверит форму ответа выражением check, не выводя тело (в нём может быть PII), и напечатает таблицу:bash ${CLAUDE_SKILL_DIR}/probe.sh [--verbose] <<'EOF' youtrack @{yt_profile} https://{yt_host}/api/admin/projects?fields=id&$top=1 - type == "array" kibana @{kibana_profile} https://{kibana_host}/api/status osd-xsrf: true - EOF - Выведи таблицу скрипта, добавь SKIP-строки и итог.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -22 lines 165cc752259a
- 1mo ago First seen · 92 lines · 40 tokens per session scan A 55f392a7075c
skills-check is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,179 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.