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/solvenpx skills add vmkteam/claude-plugins --skill solvegit 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 | $0.00065 | $0.05644 |
| Opus 5 | $0.00032 | $0.02822 |
| Sonnet 5 | $0.00013 | $0.01129 |
| Haiku 4.5 | $0.00006 | $0.00564 |
Grade A, and why
solve scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:{port}/{rpc_endpoint} \ How it starts
The opening of the file, as written. The whole thing — 482 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 human-in-the-loop на ключевых этапах.
Подключения к системам из .claude/memory/project-index.md.
Использование
/solve PLF-819 # полный цикл с 5 HITL
/solve PLF-819 --fast # ускоренный режим: 2 HITL (commit + youtrack)
/solve --fast WEB-456 # позиция флага любая
Флаг --fast
Для тривиальных багфиксов и повторяющихся паттернов. Пропускает HITL-паузы research и spec — шаги выполняются и артефакты пишутся, но пользователя не спрашивают до COMMIT.
Что делает --fast:
- ANALYZE и PLAN объединяются в одну plan-mode сессию (research.md + spec.md создаются подряд, один exit из plan mode вместо двух)
- REVIEW (/go-review) выполняется, показывается пользователю, но без отдельного HITL до коммита
- PREFLIGHT, COMMIT HITL, YOUTRACK HITL — остаются обязательными
Когда НЕ использовать:
- Сложная архитектурная задача
- Новый сервис/модуль
- Задача затрагивает больше 3 файлов
- Есть сомнения в требованиях
Если пользователь запускает /solve --fast, а задача крупная — предложи переключиться на обычный режим перед PLAN.
Артефакты
Каждый этап создаёт документ в docs/llm/tasks/{TASK_ID}/:
docs/llm/tasks/PLF-819/
├── research.md — анализ задачи, контекст, вопросы (шаг 2)
├── spec.md — спецификация плана реализации (шаг 3)
├── review-initial.md — первое ревью (шаг 9)
└── review-final.md — финальное ревью перед коммитом (шаг 9, повторное)
Flow
PREFLIGHT → FETCH → ANALYZE → research.md → ⏸
→ PLAN → spec.md → ⏸
→ TEST → IMPLEMENT → SIMPLIFY → FMT+LINT → VERIFY
→ REVIEW → ⏸
→ COMMIT → ⏸
→ YOUTRACK → ⏸
Важно:
- PLAN начинается только после утверждения research
- IMPLEMENT — только после утверждения spec
- REVIEW (/go-review) — всегда, без исключений
0. PREFLIGHT — актуальность базовой ветки
Перед любым workflow проверить, что локальный базовый бранч синхронизирован с origin. Иначе analyze/plan/review пойдут по устаревшему коду.
What ships with it
2 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.
- 2d 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 4mo ago), licensed MIT. It adds 65 tokens to every session and 5,644 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.