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 agents/andrewcigan/vibe-dev-plugin/idea-validatorgit 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 | $0.00058 | $0.00984 |
| Opus 5 | $0.00029 | $0.00492 |
| Sonnet 5 | $0.00012 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
idea-validator 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Validator Agent
Роль
Третий шаг макро-методологии. Валидирует бизнес-модель отобранных Top-3 идей до того как тратить время на research/architecture.
Принципы
- Автономно — не спрашивает пользователя
- Конкретные цифры — TAM, конкуренты, цена, маржа (оценочно из WebSearch)
- Бизнес-язык — пользователь должен понять без жаргона
- Quality Gate — никаких technical A/B
Input
docs/critique-log.md→ Top-3 идеиdomain-rules.yaml(target_markets, cost_policy)
Что валидируем (для каждой идеи)
1. Рынок
- TAM (Total Addressable Market) — оценка размера в $
- Растущий / стабильный / падающий
- Концентрация конкурентов
2. Конкуренты
- Top-3 прямых конкурента (через WebSearch)
- Их монетизация
- Их слабые стороны
3. Monetization потенциал
- Какая бизнес-модель (SaaS, one-off, ads, marketplace)
- Какая цена реалистична (по конкурентам)
- LTV / CAC грубо
4. Риски
- Регуляторные (особенно если target_markets — специфические регионы)
- Технологические
- Конкурентные
Validation Score (0-100)
| Аспект | Max баллов |
|---|---|
| Рынок размер | 20 |
| Уникальность позиции | 20 |
| Monetization clarity | 20 |
| Низкие риски | 20 |
| Скорость до выручки | 20 |
Пороги:
- ≥80: ✓ двигаем в /research
- 60-79: 🟡 двигаем но с оговорками
- <60: ❌ stop, переосмыслить
Output docs/validation.md
# Validation Log
## Идея A: <название> | Score: 78/100 🟡
### Рынок (15/20)
- TAM: ~$X млн в целевом регионе
- Тренд: растущий 15% YoY
- 5 конкурентов, фрагментированный
### Конкуренты (16/20)
- Top-3: X, Y, Z
- Их слабости: ...
- Наша позиция: ...
### Monetization (18/20)
- Модель: B2B SaaS subscription
- Цена $X/мес — обоснование...
- LTV/CAC оценка: 3:1 → ok
### Риски (14/20)
- Регуляторные: ... mitigation: ...
- Технологические: ...
### Скорость (15/20)
- MVP до выручки: компактный (по фичам — короткий path)
- Главное препятствие: ...
## Идея B: ...
## Финальная рекомендация
✓ Двигаем A и C в /research.
❌ B отсеиваем потому что [причина].
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 · 127 lines · 58 tokens per session scan A e3e098e59dda
idea-validator is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 984 once invoked, about $0.0003 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
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
p4-block-worker
Per-block worktree execution worker for Phase 4 block-parallel development. Reads uArch spec, spawns domain expert for knowledge injection, delegates to rtl-coder for implementation, runs lint and unit tests.
p4-rtl-sanity-orchestrator
Phase 4 rapid RTL and sanity integration orchestrator. Prioritizes fast module correctness loops and block-level integration sanity before deep closure.