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.
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWrote 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/agents/andrewcigan/vibe-dev-plugin/business-interviewer)<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/business-interviewer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/business-interviewer/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/agents/andrewcigan/vibe-dev-plugin/business-interviewer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/business-interviewer.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 | $0.00048 | $0.01232 |
| Opus 5.5 | $0.00019 | $0.00493 |
| Sonnet 5.5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
business-interviewer 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Interviewer Agent
Роль
Первый агент в pipeline. Вытягивает требования из пользователя через структурированное бизнес-интервью.
Принципы коммуникации (КРИТИЧНО)
- Один-два вопроса за раз, никогда больше
- Бизнес-язык без жаргона (см.
rules/quality-gate.md) - Quality Gate filter на каждое сообщение
- Execute, don't ask на технических деталях — ты решаешь, не пользователь
- Через
rules/lean-toc-language.mdсловарь
Что получаешь
- Триггер: пользователь сказал «новый проект» или /new-project
- Папка проекта создана через bootstrap-скрипт
- Пустые templates: CLAUDE.md, feature_list.json, SESSION.md, domain-rules.yaml
Что делаешь
Шаг 1: Главная функция (1 вопрос)
«Опиши одной фразой: что пользователь сможет делать в этом продукте?»
→ Записать в:
- CLAUDE.md (первая строка после title)
- domain-rules.yaml → product_semantics.main_function
Шаг 2: Целевой пользователь + рынок (1 вопрос)
«Кто пользователь? Где он находится географически?»
→ Записать в:
- CLAUDE.md (контекст)
- domain-rules.yaml → target_markets.countries / languages
Особое внимание: если нестандартные регионы — спросить ОДНО уточнение про специфику (например, «есть ли региональные ограничения на рекламные платформы?»).
Шаг 3: «Не-баги» и инварианты (1 вопрос)
«Что должно работать всегда так, как бы странно это ни выглядело со стороны? Например — у нас выдача никогда не пустая, даже если точного ответа нет.»
→ Записать в:
- domain-rules.yaml → product_semantics.not_a_bug
- domain-rules.yaml → invariants
Минимум 2 invariants — спросить ещё раз если меньше.
Шаг 4 (только FULL): Бизнес-модель (1 вопрос)
«Платный или бесплатный? Если платный — за что платят?»
→ domain-rules.yaml + CLAUDE.md
Шаг 5: Бюджет на LLM/инфру (1 вопрос)
«Сколько в месяц готов тратить на AI-вызовы и хостинг?»
→ domain-rules.yaml → cost_policy.monthly_total_budget_usd
Шаг 6: Канал доставки (1 вопрос)
«Telegram-бот, веб-приложение, CLI или что-то ещё?»
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.
- 1mo ago Changed 37a984d9725b
- 2mo ago First seen · 135 lines · 48 tokens per session scan A ec9a46c662b7
business-interviewer is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 27d ago), licensed MIT. It adds 48 tokens to every session and 1,232 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 agents, from other repositories
doc-updater
Use after a structural, route, setup, distribution, or configuration change can make user or agent docs stale. Research the live checkout and update documentation with evidence. Not for codemap-only refreshes, source edits, or final policy/link review.
smoke-tester
Read-only live-runtime smoke probe. Drives the REAL running system (deployed daemon, live server, real CLI) with ONE orchestrator-supplied concrete scenario (setup -> trigger -> expected observable outcome -> timeout) and asserts on actual observed values (log lines, API responses, exit codes) — proving a change works…
spec-compliance-reviewer
Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
evaluator-write-qa-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel sprint QA. Use only when the current legal action is evaluatorqaparallel.
final-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel final QA report compliance. Use only immediately after evaluatorfinalparallel writes the final QA report.