claude

workflow

General-purpose adversarial workflow automation with Ralph Wiggum loops. Context-aware task execution with clean subagent isolation, multi-stage verification, hook-based iteration tracking, and intelligent memory preservation before context compaction. Automatically suggests memories for patterns, decisions, lessons, and process improvements. Inspired by Goose Ralph loops and g3 principles.

3 on GitHubby Standard Beaglev0.5.3MITupdated 5 days agodevelopment
/

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

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (17)

  • workflow-add-task

    \"Add context-sized task to workflow queue via grill-task interrogation. 添加上下文適配任務至工作流隊列,通過grill-task審訊. Use when: add workflow task, queue new task, create task for loop, add task interactively, submit task to workflow\"

  • workflow-adversarial-quality

    Full adversarial quality loop — implement, self-attack, parallel verification, quality gates, final validation. 全品質循環:實現、自攻、並行驗證、質量關卡、最終確認. Use when: implement task with quality, run adversarial review, verify code quality, run quality gates, complete workflow task

  • workflow-code-quality-reviewer

    Forked-context code-quality reviewer (workflow mirror) — preloads verdict schema + coherence/bloat/completeness/duplication/cleanup lens. 對抗代碼品質審查(workflow鏡像,fork上下文)。 Use when: dispatch workflow:code-quality-reviewer subagent, adversarial code review in workflow loop, gate on quality, when reviewer

  • commit-description

    Write value-first commit message (subject + body) for staged/unstaged changes or branch work. Use when: writing commit message, about to stage changes, before commit, drafting commit body, summarizing branch work for commit. Also: writing PR description when user explicitly invokes --pr or says 'for

  • workflow-context-hygiene

    Context isolation and subagent barrier patterns for clean workflow loops. 隔絕上下文,杜絕污染,保循環清潔. Use when: prevent context leak, isolate subagent, manage loop state, enforce context barrier, fresh subagent spawn

  • workflow-loop-orchestration

    Main loop orchestration — task queue, subagent lifecycle, state machine, error recovery. 主循環協調:任務隊列、子代理生命週期、狀態機、錯誤恢復. Use when: orchestrate workflow loop, manage task queue, spawn subagent, handle loop state, recover from error

  • workflow-loop-status

    \"Show status of current or recent workflow loops with progress, metrics, and context hygiene report. 顯示工作流循環狀態:進度、指標、上下文衛生報告. Use when: check loop progress, see workflow status, how is loop going, show workflow metrics, view completed tasks\"

  • workflow-memory-management

    Preserve workflow learnings as structured memories before context compaction fires. 壓縮前保存工作流知識,結構化存儲,供日後檢索. Use when: save workflow memory, preserve lesson learned, review before compaction, store technical decision, manage memory lifecycle

  • workflow-post-task-reviewer

    Forked-context deep post-task reviewer (workflow mirror) — preloads verdict schema + OWASP + deep code + PM/docs + replan lens. 對抗深度後任務審查(workflow鏡像,fork上下文)。 Use when: dispatch workflow:post-task-reviewer subagent, deep review after fast gates, OWASP audit, PM/docs accuracy check, replan recommenda

  • workflow-qa-reviewer

    Forked-context QA reviewer (workflow mirror) — preloads verdict schema + testing-pyramid lens + assertion/edge-case/TDD checklist. 對抗QA審查(workflow鏡像,fork上下文)。 Use when: dispatch workflow:qa-reviewer subagent, adversarial QA in workflow loop, gate on test quality, when reviewer must not pollute main

  • workflow-recommender

    Routes workflow / adversarial-loop intent to right manual workflow skill — sole auto gateway, others manual. workflow 唯一自動網關。 Use when: workflow loop, Ralph Wiggum loop, adversarial cooperation, start/stop/status a loop, add or queue task, run quality gates, dispatch reviewer, save or review loop me

  • resolve-review-feedback

    Resolve review feedback by evaluating validity and fixing issues in parallel. Pre-commit-first. Use when: applying review feedback from local reviewer agent output, resolving pre-commit review findings, working through code-review agent suggestions, addressing reviewer-flagged issues before commit.

  • workflow-review-memories

    \"Search, review, and manage workflow memories — patterns, decisions, lessons, strategies. 搜索、審查、管理工作流記憶:模式、決策、教訓、策略. Use when: review workflow memories, search saved lessons, apply memory to task, find past decisions, manage memory health\"

  • workflow-setup-workflow

    \"Configure project-specific workflow role rules for adversarial loop customization. 配置項目特定工作流角色規則,定制對抗循環行為. Use when: setup workflow roles, customize task-executor rules, configure quality reviewer, set project-specific thresholds, override workflow defaults\"

  • workflow-start-loop

    \"Start Ralph Wiggum adversarial loop — context-isolated subagents, multi-stage verification, sequential task execution. 啟動Ralph Wiggum對抗循環:隔離子代理、多階段驗證、順序任務執行. Use when: start workflow loop, begin adversarial loop, run task list, start automation loop, execute tasks sequentially\"

  • workflow-stop-loop

    \"Gracefully stop currently running workflow loop with checkpoint save. 優雅停止當前工作流循環,保存檢查點. Use when: stop workflow loop, cancel loop, pause execution, halt workflow, stop current loop\"

  • workflow-testing-strategy

    Three-tier test strategy — e2e, integration, unit pyramid for disciplined coverage. 三層測試法:e2e驗產品,整合測廣度,單元窮邏輯. Use when: choose test type, write e2e test, write integration test, write unit test, debug flaky test, enforce TDD

Subagents (4)

  • code-quality-reviewer

    Independent adversarial code quality review — coherence, bloat, completeness, duplication, cleanup. 獨立對抗代碼品質審查:連貫性、臃腫、完整性、重複、清理. Use when: review code quality, check for bloat, audit completeness, find duplication, verify codebase coherence

  • post-task-reviewer

    Deep post-task review — OWASP security audit, performance, architecture, PM/docs, replan. 深度後任務審查:OWASP安全、性能、架構、文檔、重新規劃. Use when: run deep security audit, review after quality gates, check OWASP compliance, generate replan recommendations, review documentation accuracy

  • qa-reviewer

    Independent adversarial QA review — assertions, edge cases, TDD compliance, traceability, testability. 獨立對抗QA審查:斷言、邊緣、TDD合規、可溯性、可測性. Use when: review test quality, check TDD compliance, verify edge case coverage, audit test assertions, check requirements traceability

  • task-executor

    Execute a single workflow task end-to-end with clean context and adversarial verification. 以清潔上下文執行單一工作流任務,含對抗驗證. Use when: execute workflow task, run adversarial loop, complete a task with verification, spawn task executor

Hooks (2)

  • Stop
  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT}/scripts/mark-interrupted.js"

View source on GitHub dev.standardbeagle.com

More from standardbeagle/standardbeagle-tools

All 24 plugins →

agnt

claude

Browser superpowers for AI coding agents: dev-server and reverse proxy with traffic logging, a deduped priority error inbox, 50+ frontend diagnostic functions, accessibility/performance/security/SEO/responsive/API/loading audits, visual-regression snapshots, replay testing, tunnels, and sketch/design modes

36 skills · 4 agents · hooks

3

dartai

claude

Dart task management with adversarial cooperation loops and full dart-query MCP schema parity - DartQL batch operations, advanced filtering, task relationships, documents, time tracking, and automated task execution through quality verification pipelines. Requires @standardbeagle/[email protected]+ (dartai_loop_snapshot tool used by /dartai:start).

29 skills · 6 agents · hooks

3

Token-efficient Figma integration with query-based data shaping, image export, design tokens, and adversarial design library extraction. Build production-ready component libraries with exact CSS, assets, HTML mockups, and comprehensive documentation using the Ralph Wiggum quality loop.

28 skills · 4 agents

3

Contextually-loaded development standards and project-aware skills. Replaces bulk CLAUDE.md instructions with on-demand rules, language-scoped guidelines, and project-type skill templates.

25 skills · hooks

3

slop-mcp

claude

SLOP (Simple Language Open Protocol) integration for MCP management. Migrate existing MCP setups, search and execute tools, manage resources, and orchestrate multiple MCP servers. Includes Dart MCP tool reference skills for reduced get_metadata calls.

23 skills · 2 agents · 1 MCP server

3

UX-driven development toolkit for building accessible, user-centered websites and applications. Integrates UX principles, accessibility verification (WCAG 2.2), Nielsen's heuristics, and usability best practices directly into the development workflow. Includes agents for comprehensive audits and component design.

20 skills · 4 agents

3

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain workflow?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins24 plugins