By rdcrystallab
Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. Includes planning wizard, security audit, shipping workflow, autonomous debugger, and autonomous fixer.
自主除錯迴圈——科學方法 + 自動研究迭代。找出所有 bug,而非只找一個。
自主修復迴圈——迭代修復錯誤直到歸零。每次迭代修一個,原子性操作,失敗自動還原。
互動式設定嚮導——從目標(Goal)產生範圍(Scope)、指標(Metric)、方向(Direction)與驗證指令(Verify)
自主安全審計——STRIDE 威脅模型 + OWASP Top 10 + 4 個對抗性角色的紅隊測試
通用發布工作流——透過結構化 8 階段工作流發布程式碼、內容、行銷、銷售、研究或任何事物
Claude Code 插件市集,提供各種擴展功能。
| 名稱 | 說明 | 類別 |
|---|---|---|
| damage-control | 損害控制安全系統,封鎖危險指令並保護敏感檔案 | security |
| drawio | 建立和編輯 draw.io 圖表,支援流程圖、架構圖、序列圖等 | visualization |
| excalidraw | 建立手繪風格 Excalidraw 圖表,支援 PNG 匯出 | visualization |
| github-kb | GitHub 本地知識庫管理員,維護本地 repo 索引,支援 clone、查詢與 gh CLI 搜尋 | productivity |
| playwright-cli | 瀏覽器自動化,支援網頁測試、表單填寫、截圖與資料擷取 | automation |
| tmux-fork | 開啟新的 tmux 視窗以並行執行 AI agents 或 CLI 指令 | automation |
| gh-tools | GitHub 工作流程指令,管理 issues、PR 與專案 | development |
| anvil | 以證據為優先的程式碼代理人,使用對抗性多模型審查與 SQL 追蹤驗證 | development |
| autoresearch | 自主改進引擎,執行無限循環的修改驗證流程,包含規劃精靈、安全審查與自動除錯 | productivity |
# 加入市集
claude /plugin marketplace add owner/agentic-plugins
# 安裝特定插件
claude /plugin install damage-control@agentic-plugins
# 加入整個市集
claude /plugin add /path/to/agentic-plugins
# 或安裝單一插件
claude /plugin add /path/to/agentic-plugins/plugins/damage-control
agentic-plugins/
├── .claude-plugin/
│ └── marketplace.json # 市集註冊
├── plugins/
│ ├── damage-control/ # 安全插件
│ ├── drawio/ # draw.io 圖表
│ ├── excalidraw/ # Excalidraw 圖表
│ ├── github-kb/ # GitHub 知識庫
│ ├── playwright-cli/ # 瀏覽器自動化
│ ├── tmux-fork/ # tmux 並行執行
│ ├── gh-tools/ # GitHub 工具
│ ├── anvil/ # 程式碼驗證代理人
│ └── autoresearch/ # 自主改進引擎
└── README.md
每個插件目錄包含:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # 插件元數據
├── agents/ # Agent 定義(選用)
├── skills/ # Skill 定義(選用)
├── commands/ # Slash 指令(選用)
├── hooks/ # 事件鉤子(選用)
└── README.md
新增插件時請遵循:
plugins/ 下建立插件目錄.claude-plugin/plugin.json 元數據README.md.claude-plugin/marketplace.json 中註冊MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub rdcrystallab/agentic-plugins --plugin autoresearch損害控制 (Damage Control) 安全系統 - 透過 PreToolUse 鉤子封鎖危險指令並保護敏感檔案
Browser automation with playwright-cli for web testing, form filling, screenshots, and data extraction
Evidence-first coding agent. Verifies before presenting. Attacks its own output with adversarial multi-model review, IDE diagnostics, and SQL-tracked verification to ensure code quality.
使用 Excalidraw JSON 格式建立手繪風格圖表。產生架構圖、流程圖等視覺化圖表,並支援 PNG 匯出。
Fork new tmux windows to spawn parallel AI agents or run CLI commands
Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. 10 subcommands: plan, debug, fix, security, ship, scenario, predict, learn, and reason.
Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents
Meta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.