claude

crew

Virtual dev team for multi-repo legacy work - one interactive session owns a ticket from brainstorm through spec, plan, implement, tests, docs and review to done; 4 context-isolated agents (explorer, reviewer, security, researcher), a Haiku 5.5 session-relay transport agent, plus on-demand stack skills, 41 slash commands, 33 bundled skills, and deterministic hooks: a budgeted context hook (on by default) that carries the handoff across a clear or compaction, plan-approval and scope guards with a completion audit, an opt-in cloud/destructive guard, and a verify gate that fails unverified turns. /crew:migrate carries a 0.20 setup forward.

3 on GitHubby Matthew Badaliv1.3.70GPL-2.0-onlyupdated 2 days ago
/

Plugin crew from marketplace useful-claude-add-ons in mbadali25/useful-claude-add-ons. Commands read from the repo's manifest — 2 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 (33)

  • crew-best-practices

    Community best practices for working with Claude Code - context management, planning, TDD, hooks, skills, subagents, slash commands and MCP - with what crew already does, where crew departs on purpose, and what is genuinely unsettled. Use when asked how to use Claude Code well, whether a practice is

  • crew-brainstorm

    Turn a request into an approved direction before it becomes a spec - one question per message, options with the recommendation first, never implement before approval. Use at the start of any ticket that is not a known-cause one-subsystem fix.

  • crew-change

    The change-request template, the ten questions a change board requires, and how each field maps onto ServiceDesk Plus, Jira and a local file. Use when filing, checking or closing a change request, when a production promotion asks for an approved change, or when the user says change request, change m

  • crew-cloud

    Configure the official AWS and Azure MCP servers safely for a repo. Use when the user says set up AWS MCP, add the Azure MCP server, connect to my cloud account, look up AWS docs or pricing, or asks how to give the crew read access to cloud resources.

  • crew-context

    Manage context exhaustion - warn near the limit, write handoff notes, and resume work after a clear or compact. Use when the user says set up handoff, context is filling up, wrap up the session, write a handoff note, resume where we left off, or asks how to clear the session without losing state.

  • crew-debugging

    Find the cause of a defect before proposing a fix - read errors, reproduce, check recent changes, gather evidence from this repo's code map and verification map, then form one hypothesis and test it minimally. Use when encountering any bug, test failure, flaky test, performance problem or unexpected

  • crew-diagrams

    Author architecture, process, sequence, ER and data-flow diagrams as Mermaid that pass a measured readability check (no crossing lines, nothing drawn through a box, at most 15 boxes), embed them in a generated Markdown and HTML page, render them to PNG or SVG, and produce Visio files when Visio is i

  • crew-docs

    Keep CHANGELOG.md, README.md, SECURITY.md, TODO.md, ADRs, generated docs, and the API and feature reference current as work lands. Use when the user says update the changelog, keep the docs in sync, update the README, maintain TODO, document the API, list the endpoints or features, or asks which doc

  • crew-execute

    Execute an approved plan task by task, in this session - TDD per step, a ruling instead of a silent deviation, and only four conditions that stop for a check-in. Use once a ticket has an approved plan.md and implementation is starting.

  • crew-graph

    Build and query a code graph of this repository with graphify, keeping it on the filesystem as graph.json and fresh on commit. Use when the user asks to build or refresh the code graph, asks what calls what or what connects to what, or asks how a subsystem is wired. The graph lives on the filesystem

  • crew-house-style

    House style for documents the crew hands to a human - palette, heading hierarchy, capitalization, and whether the artifact should be PDF, DOCX, HTML or plain markdown. Use when exporting an architecture write-up, runbook, report or handoff, when asked what a delivered document should look like, or w

  • crew-lint

    Configure and run linters and formatters for PowerShell, PHP, Python, Terraform, and JavaScript, and wire them into the verification gate. Use when the user says set up linting, add a linter, format this code, run PSScriptAnalyzer, ruff, phpstan, or tflint, or asks why style keeps drifting.

  • crew-memory

    Conventions for durable project memory across repos, including Obsidian vault integration. Use when the user says set up memory, wire up Obsidian, connect my vault, or when writing or reading code maps, decision notes, or cross-repo contracts.

  • crew-notify

    Set up outbound notifications to Microsoft Teams or Telegram - deploy results and "Claude stopped and is waiting" questions - and explain the two-way MCP options. Use when the user says set up notifications, notify me, send to Teams, set up a Telegram bot, post updates to a channel, wire up a webhoo

  • crew-plan

    Turn an approved spec into a step-by-step implementation plan - files, tests and risk per step, no placeholders, self-reviewed against the spec before it is shown. Use once a ticket has an approved spec.md and before any code is touched.

  • crew-providers

    Set up, verify, and invoke external model providers - Codex, Kimi Code or GitHub Copilot for QA review, Gemini for design second opinions. Use when the user says set up codex, set up kimi, set up copilot, set up gemini, add a reviewer, add a design partner, configure providers, wire up the API key,

  • crew-qa-standards

    Harness, QA-review and environment standards plus a report-only audit (parallel tests, pinned linters CI really runs, gate rules that can fail, QA environment isolation, rehearsed rollback, deploys that fail loudly) and a generated QA-process doc with diagrams. Use when setting up, onboarding or upg

  • crew-runbooks

    Write, index, and maintain operational runbooks - deploys, rollbacks, alert response, recurring jobs, disaster recovery. Use when the user says write a runbook, document the deploy process, what do I do when X alerts, how do we roll this back, or asks to capture an operational procedure for later.

  • crew-setup

    Bootstrap and configure a repository for the crew workflow, as guided phases. Use whenever the user says any of - set up crew, set up the crew, set up the team, set up the virtual team, phase setup, phased setup, run the setup, initialize crew, init crew, configure crew, onboard this repo, get this

  • crew-standards

    Build-time development standards mined from crew's QA reviews. Use at /crew:plan to name the standards each step triggers, at /crew:implement for the required pre-review self-check and its stamp, and at /crew:review for the reviewer's checklist and the findings-to-standards proposals.

  • crew-terraform

    Set up and run terraform-docs and tflint for a Terraform module, including the header comment block, footer.md, and README injection. Use when the user says set up terraform-docs, generate module docs, add tflint, lint terraform, or asks why the Terraform README keeps changing or reverting.

  • crew-verification

    Build the verification map, wire test credentials safely, and set up Playwright. Use when the user asks which tests should run after a change, says set up the test map, add browser tests, add visual testing, validate UI changes, or when tests need credentials from AWS Secrets Manager, Vault, Key Vau

  • find-skills

    Discover and install agent skills from the open skills ecosystem via the skills CLI. Use only when the user explicitly asks to find, search for, browse, or install a skill or plugin - not for general "how do I" questions, which should be answered directly.

  • stack-angular

    Angular and AngularJS pitfalls, checks and verify.json wiring - change detection, RxJS composition, subscription leaks, injector hierarchy. Use when the repo has angular.json or @angular/core, or an AngularJS 1.x app, or the user asks to write or review a component, service, RxJS pipeline, or asks w

  • stack-bash

    Bash-specific pitfalls, checks and verify.json wiring - quoting, pipeline exit codes, cross-platform Git Bash surprises. Use when the repo has *.sh files, or the user asks to write or review a shell script, explain why a pipeline "passed" despite a failing command, or hits a Windows/Git Bash path-ma

  • stack-dotnet

    .NET-specific pitfalls, checks and verify.json wiring - DI lifetimes, async model, EF Core change tracking, plus a short .NET Framework 4.8 section for Web Forms/WCF legacy hosts. Use when the repo has *.csproj/*.sln files, or the user asks to write or review C#, wire up dependency injection, fix an

  • stack-node

    Server-side and CLI Node.js and TypeScript pitfalls, checks and verify.json wiring - child processes, fetch status handling, paging that says when it stopped, unhandled rejections, module format, dates and big integers - and the Node candidate standards. Use when the repo has a package.json with ser

  • stack-php

    PHP 8 pitfalls, checks and verify.json wiring - loose comparison, array key behaviour, bound SQL parameters, output escaping, unserialize, time zones - and PHP's candidate standards. Use when the repo has *.php files or a composer.json, or the user asks to write or review PHP, a PDO/mysqli query, a

  • stack-powershell

    Windows PowerShell 5.1 and PowerShell 7 pitfalls, checks and verify.json wiring - encoding defaults, TLS, module compatibility, and security hardening. Use when the repo has *.ps1 or *.psm1 files, or the user asks to write or review a PowerShell script, decide between 5.1 and 7 for a target host, or

  • stack-python

    Python-specific pitfalls, checks and verify.json wiring - mutable defaults, exception widening, the async model, text/bytes encoding - and a pointer to the gated PYTHON standards set and its candidates. Use when the repo has pyproject.toml, setup.py or requirements.txt, or the user asks to write or

  • stack-sql

    SQL Server, MySQL and PostgreSQL pitfalls, checks and verify.json wiring - sargability, NULL semantics, per-engine locking and isolation defaults. Use when the repo has a migrations directory or *.sql files, or the user asks to write or review a query, an index change, or a migration, or asks why a

  • stack-terraform

    Terraform-specific pitfalls, checks and verify.json wiring - state, plan replacements, count/for_each re-indexing, module interfaces. Use when the repo has *.tf files, a change touches a backend block or provider version, or the user asks to write, refactor or review HCL, run `terraform plan`, or ex

  • stack-web

    Playwright web UI testing pitfalls, checks and verify.json wiring - role/testid locators, web-first assertions, trace and visual-baseline discipline, accessibility via axe. Use when the repo has playwright.config.* or @playwright/test, an Angular e2e suite, or the user asks to write, review or debug

Slash commands (41)

  • /crew:approve-mass

    Approve ONE blocked mass delete, create or change - only you can, by typing this

  • /crew:approve

    Approve a ticket's plan - only you can, by typing this; the prompt hook records the receipt

  • /crew:autopilot

    Report a ticket (status), drive it until a human is needed (run), or run an approved set as parallel lanes (wave)

  • /crew:brainstorm

    Brainstorm a request into an approved direction, before it becomes a spec

  • /crew:change

    File, check and close a change request — SDP, Jira or local

  • /crew:config-setup

    Set up crew config from a menu - machine or repo layer, dry run then apply, or delete the repo config

  • /crew:config

    Show where every crew setting comes from, and set machine or repo config from a menu

  • /crew:confirm-config

    Confirm a sensitive crew config change - only you can, by typing this twice

  • /crew:debug

    Find the cause of a defect before anyone proposes a fix

  • /crew:diagram

    Create or refresh diagrams from the actual code

  • /crew:docs

    Update the documents this change should touch — and only those

  • /crew:done

    Close a ticket - needs an accepted review receipt, a clean gate, a passing completion audit, current artifacts and docs

  • /crew:emergency

    Declare an incident - stand the gates down, spin up parallel investigation lanes, and record what was skipped

  • /crew:fix

    The light path - every lifecycle phase present, each compressed to one step

  • /crew:gate

    Take a repository's merge gate down and put it back, from the export

  • /crew:graph

    The code graph - one-line status, the repo's sanctioned refresh with the pair check, and queries

  • /crew:handoff

    Write the handoff note for the next session

  • /crew:help

    What to do next, and what any crew command is for

  • /crew:implement

    Implement an approved plan for a ticket, then tests, docs and review

  • /crew:init

    Guided phased setup for this repo — resumable, one phase at a time

  • /crew:jira-sync

    Sync a ticket between Jira (via MCP) and the local cache

  • /crew:migrate

    One-time move of a 0.20 crew setup to the 1.0 layout - preview, backup, atomic apply, rollback

  • /crew:model

    Show or change which model backs each crew role, and probe that it actually answers

  • /crew:obsidian-sync

    Sync a ticket between an Obsidian Kanban board and the local cache

  • /crew:onboard

    Learn this codebase once and write a durable, verifiable code map

  • /crew:plan

    Turn an approved spec into a step-by-step plan, then get it approved

  • /crew:promote

    Promote a build to the next environment, with the full post-deploy proof

  • /crew:reference

    Generate the API, feature and integrations reference from the code, with anchors

  • /crew:review

    Independent QA review of the current diff (Codex, Kimi, Copilot, or Claude - first that probes clean)

  • /crew:runbook

    Write, update, or audit operational runbooks

  • /crew:sdp-sync

    Sync a ticket between ServiceDesk Plus (via MCP) and the local cache

  • /crew:spec

    Fill the ticket contract from an approved direction - Intent, Exclusions, Evidence, Unknowns, Touch, Acceptance checks

  • /crew:split

    Split an oversized ticket into 2-5 children, with evidence and one confirmation, in any tracker but SDP

  • /crew:status

    Read-only crew status for this repo - config, roster, tickets, review budget, gate, codemap, gitignore, handoff

  • /crew:survey

    Research the app for real gaps and propose options with tradeoffs

  • /crew:ticket

    Removed in crew 1.0 - use /crew:spec

  • /crew:upgrade

    Removed - use /crew:migrate, which upgrades a pre-0.20 config itself

  • /crew:verify

    Build or refresh the verification map from evidence

  • /crew:webtest

    Drive Playwright's Test Agents inside the ticket lifecycle - a healer skip is a finding, never accepted

  • /crew:work

    Removed in crew 1.0 - use /crew:implement

  • /crew:worktrees

    Where worktrees go (worktrees.root), a read-only survey of them, and owner-confirmed removal

Subagents (5)

  • explorer

    Read-only codebase investigator. Use proactively for any question about where code lives, how a flow works, or what depends on what. Returns a short map, never file contents. Examples: <example> Context: The user needs to know where something lives before changing it. user: "Where is the rate limiti

  • researcher

    External research only - library and framework docs, API and SDK behaviour, version and migration questions, vendor pricing and limits, standards, RFCs, prior art. Use when the answer lives outside this repository. Read-only; every claim carries its source. Examples: <example> Context: The answer li

  • reviewer

    Hostile reviewer for one change's diff, and the Claude fallback when Codex and Copilot are unavailable. The crew 1.0 successor of qa-reviewer. Never runs in the session that wrote the code. Not for a broad quality pass over unchanged code. Examples: <example> Context: A diff is ready for review and

  • security

    Read-only security reviewer. Use before merging any change touching authentication, authorization, user input, uploads, SQL, secrets, PII, infrastructure permissions, the CI/CD pipeline, or the dependency tree. Do NOT use this for actively exploiting a running system; crew ships no agent for that. E

  • session-relay

    Transport-only relay for messages between sessions, pinned to the full id `claude-haiku-5-5` (Haiku 5.5). The main session hands it what to send and to whom; it formats and sends, and condenses inbound peer messages. One per session. It is not a review or investigation role and never acts on message

Hooks (8)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" SessionStart

  • UserPromptSubmit

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" UserPromptSubmit

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" PreToolUse

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" PostToolUse

  • SubagentStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" SubagentStart

  • PreCompact

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" PreCompact

  • Notification

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" Notification

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/crew-hook.sh" Stop

View source on GitHub

More from mbadali25/useful-claude-add-ons

All 49 plugins →

Make one or more Obsidian vaults Claude Code's durable, token-efficient memory - cross-platform, multi-vault setup and health checks for the Local REST API bridge (one MCP server per vault), a vault contract guard whose frontmatter and ASCII rules ship off and whose canvas shape check ships on, gardening and reflection agents, canvas and map-of-content generation, and graphify wiring into a separate codegraphs vault.

3 skills · 11 commands · 2 agents · hooks

3

gizmoduck

claude

Nuclei vulnerability scans on hosts and websites, or the whole scanner routine (checkov, trivy, dependency-check, semgrep, ZAP, testssl, nmap, nikto, gated sqlmap) from one manifest with a coverage table and a dated docs/security-scans layout, diffed against a baseline, rendered as triaged Markdown/HTML/PDF reports that itemise Critical/High/Medium and count the rest, and turned into ServiceDesk Plus tickets for Critical and High findings after one batch confirmation. No hooks, no agents.

1 skill · 6 commands

3

localgpu

claude

Local models on your own GPU via Ollama, in two halves - three MCP tools that index a repo or folder into a vector store on disk, search it, and answer from it, plus a `localgpu` command that opens a separate Claude Code session on a local chat model through a translating proxy. Commands for setup, health checks, indexing, search, ask, and pointing crew at a local model. No hooks and no agents; no prompt, file, or embedding leaves the machine.

1 skill · 6 commands

3

Two adversarial reviewers from different model families - a Claude agent and a Codex agent - tear apart a Claude Code agent, skill or plugin against one shared rubric and return a viability verdict with cited defects, weaknesses and the edits worth making. Use when reviewing a skill, agent, command or plugin as an artifact: 'is this skill worth shipping', 'tear apart this plugin', 'will this agent's description actually trigger', 'review my SKILL.md', 'does this duplicate something we already have'. Coverage is a reported outcome: if only one reviewer runs, or the two models cannot be resolved to different families, the report says so in its own title rather than passing a single-family opinion off as two. Do NOT use for architecture, implementation plans, product ideas or code diffs - use crew's architect-reviewer, planner or code-reviewer. Standalone - its own two-model config, never crew's. No hooks.

2 commands · 1 agent

3

notify

claude

Notify a session's progress to your phone or inbox - a two-way Telegram bot (questions wait for your reply, topic-per-job dispatcher) or email over SMTP/an MCP connector.

1 skill · 1 command

3

Peer messaging between Claude Code sessions across machines - a self-hosted WebSocket bridge, an MCP client per session, a hook that wakes an idle session on a new message, and busy/idle/waiting state hooks its installer writes into your settings. Hardened fork of Peuqui/AI-Connect (MIT): per-peer tokens, no name takeover, peer content framed as untrusted, VPN-scoped listener. The watcher hook runs once installed and is silent until the plugin's own installer has run; that installer registers the MCP server and the state hooks.

hooks

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

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain crew?

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 plugins49 plugins