claude

agent-team

Seven-agent delivery pipeline with a /ship orchestrator and a human-approval gate on deploys and rollbacks.

0 on GitHubby Arnav Shahv1.1.1MITupdated 6 days agoautomation
/

Plugin agent-team from marketplace engineering-standards-marketplace in shah-arnav3/eng_standards-marketplace-claudecode. Commands read from the repo's manifest — 6 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 (1)

  • ship

    Runs the agent-team delivery pipeline end to end — Architect, Software Engineer, Reviewer, QA Test Generator, CI/CD Orchestrator, and optionally DevOps and SRE/Monitoring — routing each stage's output to the next through files, enforcing retry limits, and stopping for human approval at the design an

Subagents (7)

  • architect-agent

    Consumes a PRD (product requirements document) and produces a Technical Design Document — data structures, API schemas, and the step-by-step logic flow the engineer agent must follow. Use proactively at the start of any feature/project build, before any code is written, whenever a PRD, feature spec,

  • cicd-orchestrator-agent

    Executes code in a sandbox environment and runs the test suite, interprets terminal error output, and — on failure — captures the stack trace and returns it with fix instructions for the Software Engineer Agent. Use after the QA Test Generator Agent has produced a test suite, or any time code needs

  • devops-agent

    Packages the application and handles cloud infrastructure — generates Dockerfiles, writes Terraform or Kubernetes configuration, and, with explicit human approval, executes deployments to staging/production. Use once the CI/CD Orchestrator Agent reports a passing build, or whenever infrastructure/pa

  • qa-test-generator-agent

    Reads the code and the PRD's acceptance criteria to write automated unit and integration tests using frameworks like PyTest, Jest, or Playwright, deliberately trying to break the Software Engineer Agent's code. Use after the Reviewer Agent has approved code (or in parallel, if the pipeline runs revi

  • reviewer-agent

    Critiques the Software Engineer Agent's code before it goes to testing — reviews for readability, edge-case bugs, security vulnerabilities, and adherence to the Technical Design Document. Use proactively immediately after new or changed code is written and before the QA Test Generator Agent runs, or

  • software-engineer-agent

    Reads a Technical Design Document and writes the actual source code — creates files, installs packages, and writes modular functions matching the design. Use after a Technical Design Document exists and code needs to be written or an existing implementation needs to be extended to match a design.

  • sre-monitoring-agent

    Watches the live system — parses logs and error-tracking/metrics data (like Sentry or equivalent), alerts the team if error rates spike, and recommends a rollback for a human to approve. Read-only: it never deploys or rolls back itself. Use once the DevOps Agent has deployed a change to staging or p

Hooks (1)

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/confirm-deploy.sh"

View source on GitHub

More from shah-arnav3/eng_standards-marketplace-claudecode

All 5 plugins →

Modern OOP, functional, structural, SQL, API, Docker, cloud, and React design paradigms with code examples.

12 skills

0

Concurrency, testing, git workflows, code quality, debugging, scoped changes, documentation, performance, observability, and debloating.

10 skills

0

Backend, frontend, network, system, database, and dependency/supply-chain security scanning checklists.

6 skills

0

Token-efficient habits, per-task model and effort selection, session memory, docs-first discipline, autonomous execution, and structured work reports for Claude Code.

6 skills

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

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

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

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

Maintain agent-team?

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 plugins5 plugins