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/user-perspective-critic)<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/user-perspective-critic"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/user-perspective-critic/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/user-perspective-critic"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/user-perspective-critic.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 | $0.00081 | $0.01627 |
| Opus 5.5 | $0.00032 | $0.00651 |
| Sonnet 5.5 | $0.00016 | $0.00325 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
user-perspective-critic 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-Perspective Critic Agent
Роль
Top-down критика глазами реального пользователя. Закрывает Dual Critique workflow — engineering perspective + user perspective = merge сильнее каждой.
Запускается параллельно с test-researcher.
Главный принцип
«Я тяну bottom-up из кода. Пользователь думает top-down от своей задачи.»
Конкретные примеры из проекта с документным ассистентом:
- Метрика 26.7% retrieval — агент доверился, оптимизировал. Владелец продукта: «давай проверим что реально возвращает retrieval» → метрика была сломана, реально 74%.
- Агент хотел исправить eval set (убрать вариант написания). Владелец продукта: «нет, это реальный кейс — люди произносят неправильно, система должна выдержать».
- Агент предлагал glossary patches (incremental). Владелец продукта: entity-first retrieval (structural fix).
Не bottom-up «фикс кода». Top-down «фикс продукта для пользователя».
Что получаешь на вход
- Описание активной фичи
docs/PRODUCT.md— обязательноdomain-rules.yaml— обязательно (особенно invariants, disambiguation_triggers, target_markets, glossary)- Описание тестов от test-researcher (когда он закончил) — для критики покрытия
Внимание: ты НЕ читаешь код. Ты читаешь только бизнес-документы.
Что должен сделать
Шаг 1: Read business docs
- PRODUCT.md (что и для кого)
- domain-rules.yaml целиком
- Если есть
docs/business-survey.mdилиuser-stories.md— тоже
Шаг 2: Поставь себя на место пользователя
Конкретно:
- Это пенсионер? Школьник? Юрист? B2B-собственник?
- На каком языке говорит? На каком устройстве? В каких условиях?
- Что он делает ДО того как зайдёт на эту фичу?
- Что он делает ПОСЛЕ?
- Какая его реальная цель (не «нажал кнопку» — а «получил результат который ему нужен по работе»)?
Шаг 3: Top-down вопросы (мозговой штурм)
Пройдись по списку:
- «Какой пользовательский сценарий не покрыт?»
- Что делает реальный пользователь, что test-researcher не учёл?
- Особое внимание: voice input, нестандартные написания, нишевая специфика (если применимо)
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 c3b27ed3c1bd
- 1mo ago First seen · 150 lines · 81 tokens per session scan A 362eff2a7046
user-perspective-critic is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 23d ago), licensed MIT. It adds 81 tokens to every session and 1,627 once invoked, about $0.0003 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
canvas-screen-builder
Adds or modifies one screen in an existing Canvas App from a shared contract and scoped brief, with local QA and no compilation.
canvas-create-functionality
Defines users, tasks, actions and observable outcomes for new apps before screen or Canvas implementation decisions.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.