claude

cq

Work queue, plan register and local board for running Claude Code as an orchestrator with parallel worktree agents.

1 on GitHubby Vegard Cowie Jørgensenv0.4.1MITupdated 12 days ago
/

Plugin cq from marketplace claude-code-queue in vegardjorg/claude-code-queue. Commands read from the repo's manifest — 12 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 (9)

  • add-helper

    Add an agent file of the project's own as a custom helper agent (an optional reviewer in the work queue), scan it, read it in full, report to the owner and approve it only on the owner's yes. Also reviews a custom helper that shows "Needs review" or "Changed since approval". Use when the user says "

  • add-to-queue

    Add saved-up or new work to the work queue (scripts/.queue, `cq`) as tracks of the right size (K 90-120 min, D about 40, D+ 25-30, U about 60; small non-blocking tasks in the batch queue), with risk class, project and feature, ownership, dependencies and owner questions. Also takes a plan entry from

  • board

    Start the local queue board (kanban, plans, dependencies, statistics, "Waiting on you") for the current project and give the user the link. Use when the user types "/cq:board", "start the board", "open the board", "show me the queue board", or asks how to see the board.

  • parallel-wave

    Default way of working for ALL parallel work in this project (several agents at once, tracks in worktrees, orchestration through the work queue). Use it every time work is to be split across several agents or tracks, also when the user just says "next wave", "run in parallel" or "split across agents

  • pick

    Pick a task from the work queue (`cq`) and do it yourself in this session, following the same protocol as a queue track. Use when the user types "/pick" (suggestions for what can be picked now) or "/pick <id>" (take exactly that task), or says "pick a task", "what can I take myself" or "give me some

  • plans

    Fetch and work with plans in the plan register (scripts/.queue/plans.json, cq plan). Fetches a plan entry, a project or an area, checks status against the code with read-only Explore agents, gives a short report and waits for the owner's instruction. Saves the plan work (document, plan entry, owner

  • queue

    Take over the work queue (`cq`) as a new orchestrator session. Reads the status (queue, branches, git, delivered tracks), gives the owner a short report and asks before starting the loop. Use when the user types "/queue", "take over the queue", "start the queue", or when the previous orchestrator ha

  • setup

    Set up the current project for the work queue (claude-code-queue plugin): queue.config.json, docs, CLAUDE.queue.md, .gitignore, recommended settings, the empty queue, a smoke test, and optionally the user''s own TODOs and plans as queue entries. Use when the user types "/cq:setup", "set up the queue

  • start

    Starts a session and only answers "ready". Used when the user types "/start" (cheap way to open a session before pasting a task).

Subagents (9)

  • reviewer-challenger

    Tries to prove a delivered track WRONG. For investigations (U) and bug fixes: looks for counter-evidence, a root cause that is really a symptom, a fix that does not fix, missed callers and sources that should not be trusted. Read-only. Answers with a FINDINGS line first.

  • reviewer-design

    UI/UX review of a delivered track with visible UI. Checks usability, clear controls and states, empty, loading and error states, error messages, WCAG 2.2 AA, keyboard use, light and dark mode, and consistency with the project's design system. Read-only. Answers with a FINDINGS line first.

  • reviewer-docs

    Reviews a delivered track that mostly changes documentation. Checks that no true fact was lost in a rewrite, that a reader can find what they need, and that the docs match the code. Read-only. Answers with a FINDINGS line first.

  • reviewer-gap

    Compares a delivered track with its mission point by point. Reports what is missing, what is only partly done, what diverges from the mission, and what was done outside it. Read-only. Answers with a FINDINGS line first.

  • reviewer-security

    Security and privacy review of a delivered D+ track (access control, tenant/user isolation, secrets, personal data in logs and errors, retention). Read-only. Answers with a FINDINGS line first.

  • reviewer-tests

    Checks whether the tests of a delivered track prove its behavior. Looks for missing edge cases (boundaries, empty input, error paths, state), tests that pass even when the behavior is broken, and whether a test fails without the change. Read-only. Answers with a FINDINGS line first.

  • reviewer

    Reviews a delivered queue track of class D or D+ from the review package made by cq receive (correctness, data integrity, contracts, tests). Read-only. Answers with a FINDINGS line first.

  • track-d

    A track of class D or D+ (database, contracts, access control; effort high). Otherwise like track.

  • track

    A track of class K or U in the work queue (skill parallel-wave), also fix rounds and continuations. Own worktree, own branch, mission from docs/queue/mission-template.md.

Hooks (10)

  • PreToolUse

    node

  • PreToolUse

    node

  • PostToolUse

    node

  • SessionStart

    node

  • SubagentStart

    node

  • SubagentStop

    node

  • SubagentStop

    node

  • UserPromptSubmit

    node

  • UserPromptSubmit

    node

  • PreCompact

    node

View source on GitHub

Similar plugins

Visual workflow automation with templates, orchestration, and lifecycle management

5 skills · 8 commands · 3 agents

ruvnet/ruflo 81,589

data-agent-kit

claudecodex

This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.

37 skills

anthropics/claude-plugins-official 47,076

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

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.

85 skills · 20 commands · 19 agents · 1 MCP server · hooks

Yeachan-Heo/oh-my-claudecode 40,800

Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...

21 skills

anthropics/knowledge-work-plugins 35,601

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

alirezarezvani/claude-skills 29,725

Maintain cq?

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 pluginslisted