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 solvegit 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/solve)<a href="https://agentmods.dev/skills/vmkteam/claude-plugins/solve"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/solve/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/solve"><img src="https://agentmods.dev/badge/skills/vmkteam/claude-plugins/solve.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 | $0.00065 | $0.03627 |
| Opus 5.5 | $0.00026 | $0.01451 |
| Sonnet 5.5 | $0.00013 | $0.00725 |
| Haiku 4.5 | $0.00006 | $0.00363 |
Grade A, and why
solve 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 6d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/solve — решение задачи
Полный цикл решения задачи из YouTrack с подтверждением пользователя (HITL) на ключевых этапах. Подключения к системам — из project-index.md в auto-memory проекта и связанного с ним ~/.claude/memory/infra-{group}.md (их создаёт /onboard).
Правила
- Не коммитить и не пушить без явного подтверждения пользователя. Дополнительный коммит после пуша (упал CI, hotfix) — тоже через HITL.
- Код не менять до утверждения spec.
/go-review— всегда, в том числе в--fast.- Ветка — по ID задачи:
PLF-819,WEB-456. docs/llm/tasks/не коммитится: артефакты остаются локально и публикуются комментарием.docs/llm/tasks/должен быть в.gitignore(остальнойdocs/llm/в некоторых проектах — закоммиченная документация).- ⏸ HITL — вопрос пользователю через AskUserQuestion с перечисленными вариантами, а для research и spec — выход из plan mode через ExitPlanMode. Следующий шаг — только после ответа.
- Если задача оказалась слишком большой — предложить
/decompose. - Если после сжатия контекста описание шагов видно не полностью — перечитай
${CLAUDE_SKILL_DIR}/SKILL.md, прежде чем продолжать. - По ходу работы подключай скиллы по контексту: /gold-arch — при любом новом или изменённом пакете, менеджере, модели, RPC/MCP-сервисе, боте или интеграции; /mfd, /zenrpc, /colgen (циклы по спискам, конвертеры), /cron (фоновые и периодические задачи), /pgd или /pgmdd, /testing.
Использование
/solve PLF-819 # полный цикл, 5 HITL
/solve PLF-819 --fast # 2 HITL: коммит и YouTrack
Флаг может стоять в любой позиции.
--fast
Для тривиальных багфиксов и повторяющихся паттернов. ANALYZE и PLAN проходят в одной сессии plan mode: файл плана содержит research и spec, и один выход из plan mode утверждает оба. HITL ревью пропускается, если в ревью нет blocker/major — тогда minor/nit показываются в HITL коммита. PREFLIGHT, VERIFY, REVIEW, HITL коммита и HITL YouTrack остаются.
Не подходит для архитектурных задач, нового сервиса или модуля, изменений больше чем в 3 файлах и неясных требований. Если задача с --fast оказалась крупной — предложи обычный режим до PLAN.
What ships with it
5 files 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.
- 6d ago Changed · +1 lines fdda01283c82
- 23d ago Changed · -305 lines 93ef3d64f336
- 1mo ago First seen · 482 lines · 65 tokens per session scan A 99abba22d0b6
solve is a skill published in the GitHub repository vmkteam/claude-plugins (7 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 3,627 once invoked, about $0.0003 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…