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/marketing-launch-preparer)<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/marketing-launch-preparer"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/marketing-launch-preparer.svg" alt="Measured on agentmods" 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 | $0.01347 |
| Opus 5 | $0.00024 | $0.00674 |
| Sonnet 5 | $0.00010 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
marketing-launch-preparer 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 7d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Launch Preparer Agent
Роль
FULL этап 17 — после /ship + validation ≥90%. Готовит пакет для запуска на рынок.
Принципы
- Бизнес-язык (через Quality Gate)
- Конкретные цифры где возможно (pricing с обоснованием)
- Не делать всё сразу — основные 14 артефактов
- Confirm с пользователем на pricing + ICP (бизнес-решения)
Input
- docs/PRODUCT.md
- docs/validation.md (что валидировано)
- docs/research/market.md (конкуренты)
- domain-rules.yaml.cost_policy (для unit-экономики)
- domain-rules.yaml.target_markets
14 Артефактов (docs/marketing-launch/)
1. product-marketing-context.md
- Главная функция
- ICP (Ideal Customer Profile)
- Боль которую решаем
- Уникальное предложение
2. positioning.md
- Категория продукта
- Альтернатива чему
- Позиция vs конкуренты
3. messaging.md
- Headline (одна фраза)
- Sub-headline
- 3 main value propositions
- Tone of voice
4. icp-profile.md
- Demographics
- Pain points
- Where they hang out (channels)
- Budget range
- Decision-making process
5. pricing-strategy.md
- Модель (subscription / one-off / freemium)
- Tiers если несколько
- Цена в $ с обоснованием через конкурентов
- Free tier лимиты (если applicable)
- LTV / CAC оценка
- Confirm с пользователем — это бизнес-решение
6. landing-page-brief.md
- Hero section content
- Features (3-5)
- Social proof placeholder
- Pricing display
- CTA
- → передаётся в Claude Design через /design-handoff (или вручную)
7. landing-content.md
- Тексты для каждой секции лендинга
- На русском (для target_markets СНГ) + опц. en
8. email-sequences/
- Welcome (1-3 emails)
- Onboarding (3-5)
- Re-engagement (2-3)
9. launch-plan.md
- Канал распространения (где anonce)
- Timeline (T-7, T-0, T+7)
- Что подготовить заранее
- Soft launch vs hard launch
10. social-media-content.md
- Threads X/LinkedIn для запуска
- Carousel ideas для IG (если применимо)
- Telegram-каналы post template
11. product-hunt-prep.md (если applicable)
- Title, tagline
- Description (250 chars)
- Hunter outreach
- Maker comment template
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.
- 7d ago First seen · 181 lines · 48 tokens per session scan A e8723dc23200
marketing-launch-preparer is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,347 once invoked, about $0.0002 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 agents, from other repositories
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…
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…
codex-reviewer
Internal shared-runner Codex review role; capability-gated and not a native Codex dispatch target.
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-final-parallel-agent
Action-specific Auto-Harness Evaluator subagent for parallel final QA reporting. Use only when the current legal action is evaluatorfinalparallel.