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/andrewcigan/vibe-dev-plugin/choose-stacknpx skills add andrewcigan/vibe-dev-plugin --skill choose-stackgit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat 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 | $0.00078 | $0.00535 |
| Opus 5 | $0.00039 | $0.00267 |
| Sonnet 5 | $0.00016 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
choose-stack 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.
What it actually says
/choose-stack
Выбор стека через stack-advisor agent.
Что происходит
- Subagent
stack-advisor(Opus) читает ARCHITECTURE.md, best-practices, domain-rules.runtime_constraints + cost_policy - Match tech к bottleneck из архитектуры
- Compose стек (один, не 3 варианта)
- Cost оценка в $/мес
- Trade-offs честно
Output
docs/stack.mdinit.shсоздаётся / обновляется под выбранный стек
Дефолтный стек (если нет противопоказаний)
- Frontend: Next.js 15 + shadcn/ui + Tailwind v4 + Inter
- Backend: Next.js API routes
- DB: Supabase + pgvector
- LLM: Claude через подписку (Opus критичное, Sonnet routine)
- Parsing: opendataloader-pdf
- Tests: chrome-devtools-mcp + vitest
Финальное сообщение (обязательный формат)
Финализируй шаблоном B (см. rules/message-finalization.md):
Готово. Стек выбран — docs/stack.md.
<краткая сводка: frontend / backend / DB / LLM / parsing / tests, одна строка каждое>
Cost оценочно: ~$X/мес (в твоём бюджете $Y).
Главный trade-off: <одной фразой>.
Вопросов от меня нет. Следующий шаг — /detail-architecture (FULL) или сразу /dev-plan → /feature loop (FAST). Согласен?
Без technical A/B. Если есть выбор — рекомендация на первом месте: «Беру X — для твоего кейса даёт Y. Альтернатива была бы быстрее в разработке, но просела бы качество. Quality first.»
См. rules/no-human-days.md — без оценок в днях.
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 · 49 lines · 78 tokens per session scan A f292bdbc622e
choose-stack is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 535 once invoked, about $0.0004 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
harness-engineering-guide
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
github-gitlab
Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.