Vibe Dev v8 — harness-first pipeline для Claude Code: от бизнес-идеи до работающего продукта. 67 проверяемых механизмов (hooks из коробки): «готово» = доказано прогоном, неперезаписываемая история фич, управляемый контекст вместо авто-сжатия.
Agent
A system-architecture agent that maps how a software project should be structured. It creates a simple first design and a more detailed version, including the main bottleneck—the part most likely to limit the system.
Agent
An agent that researches recommended ways to solve difficult project areas, such as search systems, AI agents, data parsing, or Telegram bots.
Agent
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
Agent
An interview agent that asks a business owner about a new product and records the answers in project planning files.
Agent
A critical review agent for checking a database design before tables, migrations, or access rules are implemented.
Agent
An agent that prepares a structured design brief for Claude Design, a separate tool for creating interface designs. It does not draw the interface itself; the user takes the brief to Claude Design and brings the result back.
Agent
A development-planning agent that turns a detailed software architecture into an ordered list of implementable features.
Agent
An external project auditor that reviews repository files and gives seven subsystem scores from 1 to 5. It works with fresh context and does not read the previous assessment.
Agent
An agent for researching open-source GitHub repositories related to a project. It searches for several suitable repositories, clones at least one, and studies its structure and key files.
Agent
An autonomous reviewer that reduces a long list of product ideas to the strongest three to five. It checks each idea against business rules, forbidden patterns, target markets, budget limits, and scored criteria.
Agent
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.
Agent
An autonomous business-idea review agent that scores the top three ideas using market size, competitors, earning potential, and risks.
Agent
An autonomous coding workflow for implementing a feature from its description and test plan. TDD, or test-driven development, means writing failing tests before the code that makes them pass.
Agent
A market and competitor research agent that studies products solving the same business problem, including direct competitors and alternative approaches.
Agent
An agent for preparing a market-launch package after a product has passed validation. It covers positioning, target customers, messaging, pricing, and a landing-page brief.
Agent
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
Agent
An agent that orders architecture sections according to their dependencies. A dependency is something that must be ready before another part can be built; a DAG is a dependency graph without circular dependencies.
Agent
A stack-selection guide that chooses the technologies for a software project based on its main architectural bottleneck, or limiting problem. It uses a default web stack when no constraint rules it out.
Agent
A pipeline checkpoint that decides whether work is ready to move to its next stage. It reports pass, fail, or warning using specific yes-or-no checks.
Agent
An automated process for handling a development task when progress has stopped. It records what was tried, asks several language models for suggestions, combines their responses, and presents three possible next approaches to the user.
Agent
An agent that combines findings from engineering test research and a user-focused review into one test strategy. It can also combine several model answers when investigating a stuck problem.
Agent
An engineering agent that researches how similar open-source projects test a feature and proposes a focused list of verification commands. It considers normal cases, edge cases, errors, and end-to-end behavior.
Agent
A product-focused critic that examines a feature from the user's point of view. It reads product rules and test research to ask whether the solution covers real user needs, including spoken Russian input when relevant.
Agent
An agent that builds a validation set: realistic test scenarios, expected results, and yes-or-no scoring for a product or feature.