agnt

Plugin agnt from marketplace standardbeagle-tools in standardbeagle/standardbeagle-tools. Commands read from the repo's manifest — 4 days ago.

Skills (36)

• agnt-accessibility-audit

  Accessibility auditing with axe-core, ARIA inspection, contrast checks, tab order, and screen reader simulation. 無障礙稽查：axe-core、ARIA檢查、對比度、Tab順序、屏讀模擬。 Use when: audit accessibility, check WCAG compliance, check color contrast, get tab order, check ARIA, simulate screen reader, check focus indicators

• agnt-analyze-frontend

  \"Comprehensive frontend analysis including DOM, CSS, layout, and structure. 全面析前端含DOM樣式布局結構. Use when: analyze frontend code, inspect DOM structure, review CSS layout, audit page structure, diagnose rendering issues\"

• agnt-analyze-ux

  \"Analyze user experience including layout, interactions, and usability. 析用戶體驗含布局交互可用性. Use when: review UX, analyze interactions, check usability, audit user flows, evaluate interface design\"

• agnt-audit-a11y

  \"Run comprehensive accessibility audit on current page. 全面審現頁無障礙性. Use when: audit accessibility, check WCAG compliance, find a11y issues, test screen reader support, review ARIA labels\"

• agnt-audit-performance

  \"Analyze page performance including load times and network resources. 析頁性能含載時網絡資源. Use when: check page speed, audit load times, analyze network waterfall, optimize performance, find slow resources\"

• agnt-audit-security

  \"Audit page for security vulnerabilities and best practices. 審頁面安全漏洞最佳法. Use when: check security issues, find XSS vulnerabilities, audit CSP headers, review auth flows, scan for security risks\"

• agnt-audit-seo

  \"Audit page for SEO best practices and issues. 審頁面搜尋優化得失. Use when: check SEO score, fix meta tags, audit page titles, review structured data, improve search ranking\"

• agnt-browser-debug

  Complete browser debugging workflow - element inspection, layout diagnostics, interaction tracking, visual tools via agnt proxy. 完整瀏覽器除錯工作流：元素檢測、佈局診斷、互動追蹤、視覺工具。 Use when: debug browser issue, inspect element, fix layout, debug click, debug form, debug modal, browser debugging workflow

• agnt-browser-diagnostics

  Browser element inspect, layout diag, navigation (back/forward/reload/goto) via proxy exec — target iframe-wrapped, scope target:inner/outer; use __devtool.* helpers, not raw querySelector/getComputedStyle. 瀏覽器元素檢測、佈局、導航；目標恆iframe包裹。 Use when: inspect element, debug layout, z-index, overflow, box mo

• agnt-chain

  \"Chain commands to run automatically when events occur. 事發自動鏈接命令. Use when: automate command chains, trigger on events, set up command pipeline, react to file changes, event-driven automation\"

• agnt-check-errors

  \"Check for JavaScript errors in browser. 查瀏覽器JavaScript錯誤. Use when: find JS errors, check console errors, debug browser exceptions, review error log, diagnose script failures\"

• agnt-current-page

  Extract comprehensive browser page info - URL, content, navigation, links, structured data, performance, visual state. 取瀏覽器當前頁面全覽：URL、內容、導航、連結、結構資料、效能、視覺狀態。 Use when: get current page, what page is user on, extract page content, page URL, page title, screenshot page

• agnt-demo-flow

  Record + replay an interactive guided demo overlay on the live app — self-advancing walkthrough, labelled gesture affordances. 瀏覽器互動導覽。 Use when: demo a feature, create walkthrough, run walkthrough tool, guided product tour, replay a flow, show what was built, onboarding tour, step-by-step demo over

• agnt-design-md

  Populate a DESIGN.md design-system spec by harvesting real tokens (colors, typography, spacing, radius, elevation) from the LIVE running frontend via agnt proxy — not from guesses or static CSS files. 由實際運行前端提取真實設計令牌生成 DESIGN.md。 Use when: create design.md, generate design system spec, extract desig

• agnt-dev-proxy

  \"Start dev server with reverse proxy for browser debugging. 啟開發服務器反向代理以調試瀏覽器. Use when: start dev proxy, set up reverse proxy, enable browser debugging, intercept network traffic, local dev with proxy\"

• agnt-error-monitor

  Cross-source incident inbox check with dedup, priority ordering, remediation hints, periodic monitoring — not bash grep -r error / tail -f / journalctl -f / curl probes. 跨源事件收件匣去重監控。 Use when: check errors, monitor errors, browser errors, HTTP errors, process errors, error summary/dashboard, before

• agnt-error-watch

  Stream errors from proxies and processes in real time via agnt watch + Monitor - Claude reacts instantly when problems appear. 透過agnt watch + Monitor即時串流代理與進程錯誤，問題出現當下即響應。 Use when: real-time error stream, watch for errors, monitor errors live, error notification, instant error detection

• agnt-event-watch

  Stream user interactions from browser overlay in real time via agnt watch + Monitor - panel messages, clicks, sketches, design chats. 透過agnt watch + Monitor即時串流瀏覽器覆蓋層用戶互動：面板訊息、點擊、草圖、設計對話。 Use when: watch user interactions, real-time browser events, panel message stream, sketch events, design mode st

• agnt-interaction-tracking

  Track user interactions and DOM mutations for debugging click handlers, form inputs, and dynamic UI changes. 追蹤用戶互動與DOM變動，除錯點擊處理器、表單輸入、動態UI變化。 Use when: debug click handler, track interactions, DOM mutations, form validation debug, dynamic content debug, mutation rate

• agnt-lci-companion

  Use when agnt installed and user needs semantic code search, symbol lookup, or call-hierarchy analysis — points at sibling lci plugin. agnt配套：導向lci。 Use when: find symbol definition, semantic code search, explore codebase, trace call hierarchy, repeated grep on large repo

• agnt-mcp-tools

  Complete reference for all agnt MCP tools with exact parameter schemas and copy-paste examples. agnt全部MCP工具完整參考，含精確參數模式與可複製示例。 Use when: need agnt tool parameter reference, look up tool schema, find correct parameter names, check tool invocation format

• agnt-process-proxy

  Dev server lifecycle + reverse proxy mgmt — not bash npm/yarn/pnpm/vite/next dev, dotnet watch, go run, cargo run, lsof, fuser, kill, pkill, tail -f. 開發服務器與反向代理。 Use when: start dev server, manage processes, start proxy, debug API, stop process, cleanup port, restart, multi-service orchestration, be

• agnt-qa-test

  \"Comprehensive QA testing suite for current page. 全面品保測試現頁. Use when: run QA tests, validate page functionality, test user flows, check for broken features, comprehensive page verification\"

• agnt-quality-audits

  Page quality audits for DOM complexity, CSS architecture, security, SEO/meta tags, and GPU/compositor animation load. 頁品稽查：DOM繁度、CSS構、安全、SEO、合成器負載。 Use when: audit page quality, check DOM complexity, audit CSS architecture, check security vulnerabilities, validate SEO meta tags, diagnose GPU usage o

• agnt-responsive-check

  Detect responsive layout risks before they cause problems - fixed widths, touch targets, horizontal scroll, positioning issues. 響應式佈局風險預檢：固定寬度、觸控目標、橫向滾動、定位問題。 Use when: check responsive layout, detect mobile issues, validate touch targets, pre-launch mobile check, check horizontal scroll, audit fixe

• agnt-review-api

  \"Review API calls, responses, and network traffic. 審API調用響應網絡流量. Use when: inspect API calls, review network requests, check API responses, analyze request payload, debug API issues\"

• agnt-schedule

  Schedule messages to AI agent sessions with time delays. 排程代理訊息，延時投遞。 Use when: schedule reminder, delay message to agent, queue follow-up, manage scheduled tasks, set timed verification

• agnt-screenshot

  \"Take screenshot of current browser page. 截取現瀏覽頁圖. Use when: screenshot page, capture current view, take page snapshot, document visual state, capture browser output\"

• agnt-setup-mcp

  Install agnt MCP server with intelligent detection - uses ~/.local/bin if available, falls back to npx, supports slop-mcp. 智能安裝agnt MCP服務器：優先本地二進制，退而npx，支持slop-mcp。 Use when: install agnt MCP, setup agnt server, register agnt with slop-mcp, configure agnt MCP server

• agnt-setup-project

  \"Configure scripts and proxies to auto-start when opening this project. 配置腳本代理自啟於開項目. Use when: setup project automation, configure auto-start, initialize dev environment, register startup scripts, project onboarding\"

• agnt-sketch-mode

  \"Open sketch mode for wireframing on browser page. 開繪圖模式於瀏覽頁. Use when: wireframe UI, sketch layout, draw mockup, prototype design, annotate page visually\"

• agnt-sketch-visual

  Wireframing with sketch mode and visual highlighting including screenshots, overlays, and UI annotation tools. 線框圖模式與視覺高亮：截圖、疊層、UI標注工具。 Use when: create wireframe, annotate UI, sketch mode, highlight elements, take screenshot, export wireframe, draw UI mockup

• agnt-skills

  Index + router for agnt browser skills — agnt drives real browser via reverse proxy: dev server, live page navigation and inspection, DOM/CSS/layout diagnostics, console and network errors, screenshots, sketch mode, a11y/performance/security/SEO audits. Use when: picking agnt skill, debugging browse

• agnt-stop-all

  \"Stop all running processes and proxies. 止諸進程代理. Use when: kill all servers, stop dev environment, shut down proxies, clean up background processes, halt everything\"

• agnt-visual-diagnostics

  Visual overlays for layout debugging - outline elements, show grid/flex containers, typography audit, z-index analysis, interactive element visualization. 視覺疊層排版除錯：輪廓、網格、彈性、字排、z序、互動元素。 Use when: debug layout, outline elements, show grid containers, show flexbox, audit typography, check z-index, visu

• agnt-workflow

  Manage task completion workflows with enforced review cycles. 管理任務完成工作流，強制審查循環。 Use when: set up development workflow, enforce code review, prevent premature completion, track multi-phase work, require testing before done

Subagents (4)

• browser-debugger

  Specialized agent for debugging browser issues using agnt proxy diagnostics. 代理診斷除瀏覽器患之智. Use when: debug browser errors, inspect network requests, troubleshoot JavaScript issues, diagnose page rendering, trace proxy traffic

• process-manager

  Specialized agent for managing development processes and servers. 管理開發進程服務之智. Use when: start dev server, stop processes, manage background services, restart server, monitor running processes

• tdd-refactor

  Antagonistic TDD refactoring agent; runtime verification via process management, proxy, and audits. 對立測試重構，驗運行防退化. Use when: refactor with tests, verify runtime correctness, catch regressions, check performance after refactor, TDD cycle enforcement

• ui-designer

  UI design feedback agent using sketch mode and visual diagnostics. 視覺診斷繪圖反饋之智. Use when: review UI design, improve layout, sketch wireframe, analyze visual hierarchy, iterate on design feedback

Hooks (4)

• PreToolUse

  agnt hook pre-tool-use --session-id "${CLAUDE_SESSION_ID}" --project-path "$PWD"

• PostToolUse

  agnt hook post-tool-use --session-id "${CLAUDE_SESSION_ID}" --project-path "$PWD"

• Notification

  agnt hook notification --session-id "${CLAUDE_SESSION_ID}" --project-path "$PWD"

• Stop

  agnt hook stop --session-id "${CLAUDE_SESSION_ID}" --project-path "$PWD"

Similar plugins