ry-start

name: ry-start description: "Полный task lifecycle: research, plan, implement, gates, sync. Используй для: реализуй задачу. EN: full SDLC, build feature."

Purpose

Implement a task to a high-quality, scalable, synchronized state. Speed is secondary to correctness, consistency, maintainability, and clean git history.

Workflow

If context is missing, run a scoped ry-init automatically.
Understand the prompt. For ambiguity, ask concise Russian questions with options.
Research current code through Serena memories and semantic tools.
Research current docs, patterns, and alternatives through rldyour-explore.
Read references/context-sufficiency-gate.md and pass the gate before editing code.
Write a detailed plan. Verify each plan item against code using Serena before editing.
Create or use a feature branch/worktree. Use stacked PRs only when the task naturally splits into independent logical PRs.
Implement strictly by plan, adapting only after code evidence. Make frequent atomic Conventional Commits.
Provide progress checkpoints after meaningful milestones or every 2-3 completed plan groups.
Fix all issues in touched scope plus affected integration path. If wider technical debt is found, ask whether to expand scope.
Run quality gates using project scripts, rldyour-lsps, and detected stack checks.
Trigger browser validation for UI/browser-visible work unless auth blocks it; if auth blocks, report the limitation and use available evidence.
Apply security implementation guidance for security-sensitive changes; run security review only when the owner explicitly asks for review/audit/security review.
Run reviewer subagents only when the owner explicitly asks for review, audit, security review, rules review, or ry-review; otherwise skip the expensive review phase. Reviewer output transport follows references/reviewer-protocol.md: file-first reports plus compact summaries.
Run flow-post-task-sync before final response.

Deploy Intent Routing

If the owner request includes deploy, production, server rollout, sync-and-deploy, or a named deployment target, do not finish after implementation. After code validation and Serena/docs sync, route into ry-deploy with the same scope and target. If the deploy contract is incomplete, ask for the missing server, branch, environment, health-check, rollback, or credential decision before deploying. Never invent server access or deployment targets.

Automatic Helper Routing

The owner normally invokes only rldyour-flow commands and writes prompts in Russian. ry-start must route helper skills automatically instead of waiting for explicit helper skill names:

Repository/code scope: use serena-code-workflow, lsp-routing, quality-first-engineering, and implementation-discipline for изучи код, посмотри проект, реализуй, доработай, исправь, рефакторинг, ревью, архитектура, файлы, директории, symbols, or implementation scope.
Internet or best-practice research: for technical prompts such as исследуй интернет, изучи в интернете, посмотри документацию, best practices, migration, API behavior, framework/library setup, or MCP/tool sources, use tech-research first with Context7, DeepWiki, and Grep by Vercel. Add web-research when the prompt asks for internet/current/latest/source-backed information or when sources beyond the three MCPs are needed.
Browser-visible work: use browser-tool-routing and browser-validation for проверь в браузере, визуально, UI, адаптив, скриншот, pixel-perfect, user flow, or business-logic checks. Use browser-debug for console, network, runtime, layout, hydration, Lighthouse, performance, and browser-only failures.
Design/frontend UI work: use ry-design, figma-to-code, design-system-implementation, fsd-frontend-architecture, and design-validation when the task mentions Figma, дизайн, UI, верстка, дизайн-система, shadcn/ui, ReactBits, FSD, tokens, or pixel-perfect design.
Security-sensitive work: use owasp-top-10-implementation during auth/authz/API/input/file/dependency/config/secrets/payment/admin/external-integration work. Use ry-sec-review and flow-security-review only for explicit security-review requests.
Explicit review requests: when the prompt asks for review, audit, ry-review, ry-sec-review, ry-rules-review, reviewer subagents, or rules/security review, route the matching reviewer tracks. A normal ry-start implementation request is not review permission.
Verification and finish: use verification-quality-gates, serena-memory-sync, and flow-post-task-sync before final delivery when the task produced durable code, config, docs, plugin, memory, hook, or workflow changes.

Context Sufficiency

Do not implement from a shallow prompt. Before editing, the model must know the relevant architecture, files, symbols, DB/schema/API/config contracts, tests, integration paths, current project patterns, and current external API/framework guidance needed for the task.

If the model cannot answer the gate questions in references/context-sufficiency-gate.md, it must gather more evidence through Serena, LSP, rldyour-explore, browser/security/design workflows, or ask the owner with options. This is a quality guard, not a hard blocker: the correct response is to enrich context until implementation is safe.

Reviewer Opt-In

Invoking ry-start alone is not permission to use parallel reviewer subagents. Reviewer track skills are orchestrated only by explicit review intents such as ry-review, ry-sec-review, ry-rules-review, "сделай ревью", "security review", or "аудит". Prompts must be self-contained and read-only for reviewers.

Non-Negotiables

No hacks, temporary workarounds, or untracked debt in touched scope.
No fake green checks. If a check cannot run, say why.
No silent destructive git actions. Branch/worktree cleanup requires verified merged state.
No secrets in commits, logs, docs, memories, or prompts.