claude-code-plugins

Orchestrate parallel implementation of multiple beads across cmux panes in dependency-aware waves. Use when implementing a whole feature area, dispatching multiple beads at once, or running parallel cld -b sessions. MUST USE when user says "wave", "parallel beads", "implement all beads for X", "start the beads", or references implementing more than 2 beads at once. Also triggers on "cmux dispatch", "multi-bead", "wave orchestrator".

Audit a repo for ADR hoist debt and pre-trinity packages. Triggers on: adr gap, hoist debt, adr audit, pre-trinity packages, architecture drift.

Troubleshoot beads Dolt failures: `bd dolt` push/pull errors, merge conflicts, embedded/shared-server mode problems, remote auth issues, local DB recovery, re-clone, reflog restore, broken `.beads` Dolt config, and brew-services Dolt lifecycle. Use whenever beads sync or Dolt infrastructure is failing — symptoms like "beads do not sync", "cannot push issues", "no common ancestor", "not supported in embedded mode", "Dolt server unreachable", or "lost local database". Read the beads changelog first. Do not use for normal beads tracking (`bd create/ready/close`), standalone Dolt databases, or regular git push/pull.

Create and review agents (subagents). Use when creating specialized AI assistants, reviewing/auditing existing agents, deciding between agent vs skill vs command, or asking about agent best practices, multi-agent pipelines, and model selection. MUST BE USED when the user says "create agent", "new subagent", "review agent", "audit agent", "agent vs skill", or asks about multi-agent architecture.

Query per-bead token cost metrics from the local agent metrics database. Shows cost table, impl:review ratios, most expensive beads, cost trend over time. Triggers on: bead metrics, token cost report, bead costs, /bead-metrics.

Structured 4-stage retrospective for completed beads: Requirements vs Strategy, Strategy vs Execution, Iteration Review, Workflow Audit. Creates Trap/Pattern/Decision artifacts. Use when debriefing a bead, capturing session learnings, or running a compound retrospective.

Smart bead creation with type guidance, size routing, and auto-scenario generation for features. Use when creating beads, adding work items, or when user describes something to build/fix/improve. Triggers on bead erstellen, create bead, neues bead, new bead, bd create.

Guided planning dialog for larger initiatives producing Beads epics with sub-tasks. Use when planning features or multi-task initiatives needing structured breakdown. Triggers on epic init, plan epic, create epic, plan feature, break down feature.

intake — Transkript zu Beads Pipeline

Refactor Note

Run a data-driven bi-weekly retrospective using open-brain timeline, bead metrics, and git history. Detects signals, selects a matching retro method, and guides 4 reflection rounds. Use when running a retro, sprint review, or bi-weekly reflection.

Review Conventions

Review a wave or epic subtree before dispatch. Finds defects single-bead review misses: dependency ordering, ownership collisions, lifecycle contradictions, validation gaps. Triggers on wave review, review wave, pre-wave review, bead tree review.

workplan — Beads-Backlog analysieren, priorisieren und verbessern

Structured AI-Readiness Self-Assessment across 6 dimensions. Use for career planning or evaluating AI capability readiness. Triggers on AI readiness, self assessment, AI capability check, career readiness, AI skills assessment.

Amazon.de automation via playwright-cli with local purchases database. Use for downloading invoices, searching order history, or querying past purchases. Triggers on amazon rechnung, amazon bestellung, amazon order, was habe ich gekauft.

Professionelle Angebote fuer IT-Projekte und Beratungsleistungen erstellen. Use when writing proposals, revising offers, or calculating project pricing. Triggers on Angebot, proposal, Preiskalkulation, Angebotserstellung, offer, Beratungsangebot.

Modulare Karriere-Analyse fuer die AI-Aera mit Collapse Position Audit und Role Assessment. Use when evaluating career positioning or assessing AI impact. Triggers on career check, career analysis, career collapse, AI career, role assessment.

CLI wrapper for Collmex Buchhaltung Pro API. Use when managing vendors, invoices, open items, bookings, or generating ZUGFeRD XML. Triggers on Collmex, accounting, invoices, payables, vendors, Buchhaltung, Lieferanten, offene Posten.

Multi-perspective sequential document review. Orchestrates 4 specialized Haiku subagents that critique a document from different angles (End-User, Developer, Security, Product Owner for requirements; configurable per type). Produces a consolidated findings table sorted by severity. Use when reviewing specs, requirements, deliverables, or training materials.

Download Google One AI Pro invoice from payments.google.com, generate ZUGFeRD XML, and send to accounting. Triggers on google rechnung, google invoice, google one beleg, google one rechnung.

Send emails with attachments via Apple Mail AppleScript automation. Prepares a visible draft for user review before sending. Use when sending emails with file attachments. Triggers on send email, mail send, email with attachment, mail schicken.

CLI for MoneyMoney macOS finance app via AppleScript. Use when querying accounts, balances, transactions, cashflow, or spending. Triggers on MoneyMoney, bank accounts, transactions, cashflow, spending, balance, portfolio, financial analysis.

Read, list, and create service credentials in 1Password. Use when needing API keys, service passwords, or creating credentials. Triggers on 1password, 1Password, op credentials, api key, service credentials, op read, op://, op item, vault, password speichern. Not for personal logins or SSH keys.

Create, review, and manage voice/brand profiles for Claude Code skills. Use when creating brands, reviewing quality, or applying voice profiles. Triggers on create brand, voice profile, review brand, change tone. Not for skill creation.

End-user browser automation with cmux. Use when you need to open sites, interact with pages, wait for state changes, and extract data from cmux browser surfaces.

Open markdown files in a formatted viewer panel with live reload. Use when you need to display plans, documentation, or notes alongside the terminal with rich rendering (headings, code blocks, tables, lists).

LinkedIn automation and data analysis via playwright-cli. Use when extracting profiles, reading feeds, writing recommendations, or searching people. Triggers on LinkedIn, profile extraction, connections, feed, LinkedIn search, recommendation.

Design UI screens and components in Pencil .pen files via MCP tools. Use when creating designs, editing .pen files, or working with design systems. Triggers on pencil, pen file, design system, design screen, components.pen.

Transcribe audio files with speaker diarization via AssemblyAI. Supports local files and Plaud AI cloud recordings.

End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.

Generate and manage daily project briefs. Reads from and writes to open-brain as the system of record (type=daily_brief). Disk write is opt-in via --persist-disk. Use for daily summaries of git activity, bead progress, and open-brain entries across tracked projects.

Query the structured event log for any project. Shows tool use history, session starts, permission decisions, and errors from the centralized harness events database. Use when investigating session activity, debugging tool usage patterns, reviewing what happened in a session, or querying across projects.

Refine raw, unstructured, or dictated user input into a structured prompt via HeyPresto MCP, then EXECUTE the refined prompt immediately. Use when the user provides messy dictated text, vague task descriptions, or says "expand prompt", "refine prompt", "use heypresto", "prompt verbessern". Also triggers on "Expand Prompt." at the start of a message followed by stream-of-consciousness text. Do NOT use for simple direct questions or already-clear prompts.

Manage coding standards lifecycle - list, inject, create, sync, review. Use when loading standards, checking compliance, creating new standards, or syncing standards to projects. Triggers on standards, inject standards, load standards, check compliance, create standard, sync standards, review conventions, check patterns, apply patterns.

Content extraction and summarization via summarize CLI and Crawl4AI. Use for extracting web content, YouTube transcripts, podcasts, and generating AI summaries.

Unconstrained creative brainstorming and lateral thinking mode. No quality gates, no feasibility checks, no task tracking — pure idea generation. Use when the user says "vision", "brainstorm", "Kreativmodus", "was wäre wenn", "what if", or wants to explore possibilities without constraints.

Reverse-engineer desktop apps to understand how they work under the hood — APIs called, internal flow, models/providers, feature flags, config constants, embedded prompts, IPC. Covers Electron apps (Slack, Discord, VS Code, Cursor, Notion, Linear, Wispr Flow…), macOS .app bundles, single-executable bundles (Bun/Node/Deno/Go SEA), and raw Mach-O / ELF / PE binaries. Triggers when the user points at a desktop app path (.app, .exe, binary) or asks "how does X work under the hood", "what API does it call", "what endpoints does it hit", "what model does it use", "reverse engineer this app", "does it run locally or in the cloud", or wants to audit network behavior / extract embedded strings/prompts/secrets. Do NOT use for the user's own source code (just read it), web apps without a desktop client, or the Claude Code binary (use claude-binary-explorer for that — it knows Claude Code's mangled variable conventions).

Structured 4-phase bug investigation: Reproduce → Root Cause → Fix → Regression Test. Use when a bug is reported, something is broken, "geht nicht", Fehler, regression detected, or kaputt. Guides through systematic investigation instead of guessing.

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".