Autonom8-Agents

Merges bookend agent reports into revised readiness, complexity, and decomposition plan. Produces the final evidence-backed assessment consumed by sprint-architect-agent.

Fast filesystem readiness scan — counts docs, source files, manifests, platform signals. Produces initial ReadinessReport for agent spawning decisions.

Scores proposal complexity against codebase surface. Uses proposal text analysis and readiness stats to determine decomposition tier and agent count.

Generation-time design taste for web UI work. Anti-cliche bans, layout and motion hard rules, and client-intent dials. Advisory only - shapes drafts; declared measured contracts remain the sole gate authority.

Rigorously reasons about definitions, proofs, and computations in algebra, analysis, discrete math, probability, linear algebra, and applied math. Verifies derivations, spots invalid steps, and states assumptions clearly. Use when solving or proving math problems, reviewing mathematical arguments, modeling with equations, interpreting statistics, or when the user mentions proofs, lemmas, theorems, integrals, series, matrices, optimization, or numerical methods.

Visual verification for interactive elements (popups, modals, tooltips). Clicks elements and captures screenshots for analysis. Bypasses MCP browser tool limitations with cross-origin CSS.

Create Flutter widget_test fixtures for UI components. Uses golden_toolkit for snapshot testing with multi-device and theme support.

Create iOS XCTest fixtures for UI components. Uses swift-snapshot-testing for visual validation across devices and traits.

Create HTML test fixture AND Playwright spec for UI components. Uses project templates to create isolated test pages for TDD validation. Web-specific enhancement creates both files.

Proactive audit for third-party component theming conflicts. Detects libraries that inject default styles and mandates explicit override patterns before implementation.

Generate Playwright test specs from UI components. Creates test scaffolding with selectors, fixtures, and common interactions.

Verify cross-file integrations. Checks CSS class references, imports/exports, component usage, and asset paths. Returns JSON with validation results.

Run Playwright tests with intelligent port detection. Reuses existing dev servers to avoid port conflicts. Returns JSON with test results and server status.

Automated code review for security, design tokens, and accessibility. Checks for XSS, hardcoded colors, missing ARIA attributes. Returns JSON with issues.

Augment test fixture with edge cases, accessibility tests, responsive breakpoints. QA skill that ensures comprehensive test coverage.

Create HTML test fixture for UI components. Uses project templates to create isolated test pages for TDD validation.

Validate UI component fixture in browser. Opens test page, checks rendering, captures console errors and screenshots.

Accessibility audit using axe-core. Checks WCAG 2.1 compliance, keyboard navigation, ARIA attributes, and color contrast.

JavaScript bundle analysis. Checks bundle sizes, tree-shaking effectiveness, duplicate dependencies, and chunk splitting.

Update CATALOG.md incrementally from a deployed ticket. Appends new files_created entries without regenerating entire catalog.

Import/export validation post-implementation. Checks that all imports resolve to actual exports, catches broken references and circular dependencies.

CSS quality audit. Checks for unused selectors, specificity issues, duplicate rules, and design token compliance.

Pre-deployment validation. Verifies files exist, no broken references, build succeeds, and critical paths work before marking ticket deployed.

Generate CATALOG.md from deployed tickets. Extracts files_created metadata and builds project asset catalog with usage instructions.

Code linting during review. Runs ESLint/Prettier/platform-specific linters on changed files. Returns warnings and errors with fix suggestions.

Backend QA for API/Lambda/gRPC testing. Validates endpoints, response schemas, error handling, and integration tests. Returns JSON with test results.

Fast browser health check for web pages. Catches 404s, console errors, and missing assets. Returns JSON with check results per URL.

Data QA for database migrations and schema validation. Checks SQL syntax, UP/DOWN sections, model-schema consistency, and rollback safety.

Exploratory QA to find edge cases and unexpected bugs. Tests boundary conditions, error states, and unusual user flows.

Performance validation for web apps. Checks Core Web Vitals (LCP, FID, CLS), bundle sizes, resource counts, and lighthouse scores. Returns JSON with metrics.

Fast pre-QA sanity check. Validates files exist, server responds, and basic page loads before running full test suite. Returns JSON with pass/fail status.

Visual QA for Flutter apps using golden_toolkit snapshot testing. Validates widgets render correctly across devices and themes.

Visual QA for iOS apps using swift-snapshot-testing. Validates UIKit/SwiftUI views render correctly across devices and traits.

Visual QA for HTML/CSS/JS web apps. Validates layout, animations, styling, i18n keys, data display, and interactive elements using Playwright.

Pre-implementation ticket validation. Checks required fields, platform compatibility, and dependency status. Returns JSON with validation results.

Security vulnerability scanning. Detects OWASP Top 10 issues, hardcoded secrets, XSS, SQL injection, and insecure dependencies. Returns JSON with findings.

Pre-decomposition ticket validation. Fast structural check for required fields, platform detection, and dependency status. Blocks invalid tickets early.