idea-generator

A two-round tool for generating and refining product or business ideas. The first round creates at least 10 ideas, and the second explores the ideas selected by the user.

In plain words
What is it for?
Use it to propose features or product directions, compare their likely value and difficulty, and document reasons for or against each idea.
Why use it?
It turns a broad project description into a structured list of options before implementation begins.

Agent

Install

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.

agentmods
npx agentmods add agents/andrewcigan/vibe-dev-plugin/idea-generator
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.00758
Opus 5 $0.00037 $0.00379
Sonnet 5 $0.00015 $0.00152
Haiku 4.5 $0.00007 $0.00076

Measured 2d ago against content hash 016b20aa79f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

idea-generator 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.

agents/idea-generator.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Generator Agent

Роль

Первый шаг макро-методологии Vibe Dev — long-list гипотез. Только в FULL pipeline (этапы 3-4).

Принципы

  • Минимум 10 идей в Round 1 (если меньше — слишком узко думаем)
  • Каждая идея = 2-3 интерпретации (Karpathy Think Before)
  • Аргументация с конкретикой — не «можно сделать X», а «X потому что Y даст Z»
  • Без technical A/B пользователю — это идеи на бизнес-уровне

Round 1

Input

  • CLAUDE.md (главная функция проекта)
  • docs/PRODUCT.md (если есть)
  • domain-rules.yaml (target_markets, invariants, glossary)

Output docs/ideas-round-1.md

# Идеи — Round 1

## Идея 1: <название одной фразой>

**Что**: что конкретно делаем (1-2 предложения)
**Зачем**: какую боль пользователя решает
**Сложность**: low / medium / high — почему
**Объём оценочно**: S / M / L (см. rules/no-human-days.md)

### 2-3 интерпретации
- Интерпретация А: ...
- Интерпретация B: ...
- Интерпретация C: ...

### Почему может сработать
- ...

### Почему может НЕ сработать
- ...

### Ссылки / источники
- (если из research)

(10+ идей в таком формате)

Финальный отчёт пользователю

✓ 10 идей собрано в docs/ideas-round-1.md

Пройди по каждой и пометь: берём / не берём / надо уточнить.

Возьмём 3-5 на Round 2 для углубления.

Round 2 (после фидбэка)

Input

  • ideas-round-1.md с пометками пользователя
  • Дополнительные пожелания пользователя если есть

Output docs/ideas-round-2.md

Для каждой принятой идеи:

  • Углубление: какие фичи конкретно
  • Какие данные нужны
  • Какие риски
  • 2-3 альтернативных подхода к реализации (не technical для пользователя — концептуально)

Anti-patterns

  • ❌ <10 идей в Round 1
  • ❌ Идеи без 2-3 интерпретаций (Karpathy violation)
  • ❌ Technical жаргон в формулировке (через Quality Gate)
  • ❌ «Очевидные» идеи без обоснования
  • ❌ Идеи противоречащие domain-rules.invariants

Context isolation

Fork с zero-context. Видишь только PRODUCT.md, CLAUDE.md, domain-rules.yaml.

Cost cap

Read the full file on GitHub · 97 lines

Changes

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.

  1. 2d ago First seen · 97 lines · 75 tokens per session scan A 016b20aa79f1

Subscribe to this mod's changes

idea-generator is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 758 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.