By agentx-team
A cloud-native software delivery agent team. Seven roles across a Build → Ship → Accept → Promote lifecycle (planner, engineer, reviewer, operator, black-box e2e-tester, marketer, coordinator) and four workflows, building one monorepo derived from github.com/aws300/scaffold. Local-first; the same agents deploy headless to Claude Managed Agents via scripts/cma.
Start here — clarify what you want, then route into the right studio workflow across the full lifecycle (build → ship → accept → promote)
Show the current state of the studio's Build → Ship → Accept → Promote lifecycle — active workflow/stage, last verdict, blockers, next action
Dispatch one dev-studio role directly — /dev-studio:agent <role> <task> delegates the task to that specialist (planner|engineer|reviewer|operator|e2e-tester|marketer|coordinator), skipping the workflow gates
Run a dev-studio workflow by name — /dev-studio:workflow <name> <input> routes to deliver-service | ship-service | accept-service | promote-service (same as the /dev-studio:workflows:* commands)
Deliver a service end to end — plan, build (backend + frontend + tests) from the scaffold, then adversarial code + security review, packaged for sign-off
Turns a short service request into a service contract with binary, testable acceptance criteria, scoped to the team scaffold repo (github.com/aws300/scaffold). Use at the START of a workflow to convert a 1–4 sentence ask into the contract the engineer builds against and the reviewer grades against. Not for implementation — it scopes and defines "done" (use the engineer for the build).
Implements a service against the approved contract — proto-first ConnectRPC backend (Go/Python), SolidJS frontend, and tests — by following the scaffold repo's own scripts and CI. Use AFTER the plan is approved. It builds, then hands off to the reviewer; it does NOT self-evaluate and does NOT advance on a FAIL.
The adversarial Evaluator — its job is to FIND FAILURES, not confirm success. Use to challenge the plan before a build (APPROVE/REVISE), the build after the engineer finishes (PASS/FAIL), the release before ship (GO/NO-GO), and the promo materials for accuracy (GO/NO-GO). Verifies against the scaffold repo's own CI gates. The single most important role for output quality.
Packages a reviewed service for the team's Kubernetes cluster and wires it into the running platform — Helm release, Envoy route, IRSA, and observability against the cluster's existing Prometheus/Loki/Tempo/Grafana — following the scaffold repo's deploy scripts and CI. Use after delivery. It produces a staged deploy + rollback plan and observability config; the live deploy stays a human action.
A BLACK-BOX acceptance Evaluator. It NEVER sees source code — given only the deployed product URL, API base URL, and Grafana URL, it exercises them with a browser and HTTP/API tools and judges UI consistency, API consistency + stability, cloud-native observability coverage, and log coverage. Use to accept a DEPLOYED service. Issues a scored PASS/FAIL; FAIL loops back to the engineer (UI/API/log) or operator (observability).
个人知识库(Obsidian wiki vault)的唯一入口与控制面:记录、调研、蒸馏、摄入、查询、维护、可视化、自动化,一站式覆盖。 Use this skill whenever the user wants to interact with their wiki / knowledge base / second brain / notes in any way — 写入或读取都走这里。触发词包括但不限于:"wiki", "记到 wiki", "帮我记录今日笔记/工作日志", "帮我记录会议纪要", "记一下今天做了什么", "帮我调研某个 URL / 调研一下 X", "记录一下这个客户沟通", "帮我写周报/月报", "整理成文档存到 wiki", "把最近的笔记蒸馏一下 / 提炼知识 / 整理成概念页", "ingest 这些文档/PDF/网页", "导入我的 Claude/Codex 对话历史", "我知道关于 X 的什么 / 查一下 Y", "audit/lint 我的 wiki / 找坏链孤儿页 / 健康检查", "补交叉引用 / 归一标签 / 查重合并", "wiki 状态/进度", "导出图谱 / 着色 / 建仪表盘", "初始化/重建 vault", "设置定时任务/自动维护/自动周报", "log this", "record today's work", "research this url and save it", "distill my notes", "query my wiki", "lint/audit my wiki", "ingest these docs", "set up a cron for my wiki", "请使用 skill wiki 管理/处理这个文档" (bind an attached document as the vault). 它把零散口语扩写成专业中文文档并 归档(日报/周报/月报、会议纪要、技术调研、日记),自动滚动汇总,蒸馏 journal/_raw 为知识页,并通过内置 框架手册覆盖 obsidian-wiki 的全部 AI 能力(ingest/query/lint/cross-link/dedup/export/research/history-ingest/ dashboard/rebuild 等)。vault 通过 .config/skills/wiki/wiki.json 绑定(先查 cwd,再查 ~),可关联任何本地 git 目录或 AgentX 附加的 Library 文档;每次写完自动同步(git commit & push,或 AgentX 内走 save_document)。
Acceptance-test a deployed product as a black box — drive the live UI and API, then verify observability and logs in Grafana — judging UI consistency, API consistency + stability, observability coverage, and log coverage WITHOUT seeing source. Use by the e2e-tester. Triggers on "acceptance test", "e2e test the deployed product", "is the live service correct", "black-box test".
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Build a service from the team scaffold (github.com/aws300/scaffold) — proto-first ConnectRPC backend (Go 1.26 / Python 3.13) + SolidJS frontend — by following the repo's OWN scripts and CI rather than re-explaining the stack. Use when: implementing a new service or feature, regenerating proto stubs, or running the local build/lint/test loop before review. Triggers on "build the service", "implement the backend", "scaffold", "regenerate protos", "make the frontend". Not for: deploy/Helm packaging (use deploy-pipeline) or black-box acceptance (use webapp-testing).
Produce a search-driven, multi-dimension market assessment for a shipped product — comparable products, competitive positioning, market dimensions, and recommended go-to-market directions, every claim cited. Use by the marketer. Triggers on "market assessment", "who are the competitors", "comparable products", "market positioning", "go-to-market".
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
default_modelModel the Sonnet-tier roles (planner, engineer, reviewer, operator, e2e-tester, marketer) run on. The coordinator always runs on opus. Maps to CMA_MODEL for headless deploys.
${user_config.default_model}reviewer_strictnessHow skeptical the reviewer and e2e-tester are: 'standard' (default thresholds), 'strict' (raise every blocking threshold and require evidence per criterion), or 'panel' (multiple independent reviewers on high-stakes gates).
${user_config.reviewer_strictness}External network access
External network access
Connects to servers outside your machine
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A curated directory of high-quality plugins for Claude Code.
⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information.
/plugins - Internal plugins developed and maintained by AgentX/external_plugins - Third-party plugins from partners and the communityPlugins can be installed directly from this marketplace via Claude Code's plugin system.
First, add this repository as a plugin marketplace:
claude plugin marketplace add agentx-team/claude-plugins
Then install a plugin from it:
claude plugin install {plugin-name}@agentx-plugins
If you already have the agentx-plugins marketplace added, refresh its manifest first, then install:
claude plugin marketplace update agentx-plugins
The name after
@is the marketplace name defined in.claude-plugin/marketplace.json(agentx-plugins), not the GitHubowner/repopath.
Alternatively, browse for the plugin in /plugin > Discover
Third-party partners can submit plugins for inclusion in the marketplace. External plugins must meet quality and security standards for approval. To submit a new plugin, use the plugin directory submission form.
Each plugin follows a standard structure:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # Plugin metadata (required)
├── .mcp.json # MCP server configuration (optional)
├── commands/ # Slash commands (optional)
├── agents/ # Agent definitions (optional)
├── skills/ # Skill definitions (optional)
└── README.md # Documentation
The name field in a marketplace entry is an immutable slug. Once a plugin has been published, its name must not change — users have it installed under that slug, and renaming it breaks their install with a plugin-not-found error.
displayName instead.renames map in .claude-plugin/marketplace.json so existing installs auto-migrate:"renames": {
"old-name": "new-name"
}
The Claude Code plugin loader reads this map and transparently rewrites the old slug to the new one on the user's next sync.
When a plugin's source repository ships skills (SKILL.md files) without a .claude-plugin/plugin.json manifest, the marketplace entry can declare the skills directly using strict: false and an explicit skills array.
{
"name": "example-bundle",
"description": "Brief description of the bundled skills.",
"author": { "name": "Author Name" },
"category": "development",
"source": {
"source": "git-subdir",
"url": "https://github.com/example-org/sdk.git",
"path": "packages/agent-skills",
"ref": "main",
"sha": "<commit sha>"
},
"strict": false,
"skills": [
"./skill-a",
"./skill-b",
"./skill-c"
],
"homepage": "https://github.com/example-org/sdk"
}
Each path in skills is relative to source.path and points at a directory containing a SKILL.md. Paths can reach deeper than a single level — for example, ["./libA/skill-1", "./libB/skill-2"] exposes a curated subset across multiple library subdirectories. Each skill is registered as <plugin-name>:<skill-name> in Claude Code.
For the underlying schema, see Strict mode in the marketplace documentation.
Please see each linked plugin for the relevant LICENSE file.
For more information on developing Claude Code plugins, see the official documentation.
npx claudepluginhub agentx-team/claude-plugins --plugin dev-studioBind a Claude Code session to an IM chat room; push long-task results to the room on completion.
A domain-agnostic agent-team scaffold built around the Planner → Generator → Evaluator loop. Reusable role agents and a reference end-to-end workflow, with plugin-level hooks, MCP/LSP registration, monitors, output style, and user config. Local-first; the same agents deploy headless to Claude Managed Agents via scripts/cma.
Start-from-scratch session utilities: /scratch:fresh rescans ~/.claude (skills, plugins, agents, commands, MCP) so a new session in the current directory knows everything available; /scratch:takeover finds another directory's Claude session, absorbs its history into the current context, moves its files here, and continues the work.
Push Claude Code notifications (turn results, human-in-the-loop alerts) to a shared IM chat room. Outbound-only, zero LLM tokens, no Node.js.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.