A command is the one you type. It runs exactly when you ask it to, and never before.
9,228 commands across 665 plugins.
Consult current practice for a task — search the Skill Federation, read several skills as field notes, install only what you'll reuse
Use `sgrep` for semantic and hybrid search across **code** and **agent conversations**. It understands intent, not just exact strings.
Run polygen — draft a contract from a feature description, author a verifiable SAM v2 strict-profile module against it, self-repair against reachable invariant…
Run polynv — elicit the invariants for a state machine. Harvest candidates from the contract's vocabulary, traces, and fleet snapshots; contribute…
Run polyvers — classify a state-machine version change into compatibility lanes, run the gates those lanes require against fleet snapshots (shape round-trip,…
Generate, edit, or create any image — photos, illustrations, website visuals, placeholders, icons, thumbnails, banners, or any graphic asset
Advance Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build [sprint]
Advance parallel Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build-parallel [sprint]
Run the full Auto-Harness orchestration flow. /auto-harness:harness <brief or clarification/spec-approval reply>
Generate/maintain the openwiki/ documentation wiki (init | update)
Create a dedicated worktree for a story and open a new VS Code window on it, ready to run the pipeline. Usage - /launch-story PROJ-1234
Turn an idea, brief, or document into a well-formed backlog and create it in your tracker after approval. Guided by default; --quick for a one-shot draft.…
Turn a spark (an idea, even a one-liner) into a clear product definition through a guided discovery phase, then hand it to plan-backlog. Facilitate, never…
Configure this project for Obsidian PKM — connects the repo to a vault project folder and writes CLAUDE.md integration directives
CodeCrew - Multi-agent orchestration with intelligent model routing. Subcommands: init, task, status, reindex
Create, list, or remove custom project-specific agents. Subcommands: create, list, remove.
Configure CodeCrew settings - model tiers, default mode, token budgets, and more. Subcommands: show, set, reset.
Save wave state to disk so an auto-compact, session crash, or laptop battery death doesn't kill the run. Run this between phases or before any long operation.
Start a new wave. Default runs the canonical v2 framework (17 phases + conditional [DR] for UI waves at 1.5 + optional [CR] gate at 3.5, max 19). Pass --demo…
Hold what you've actually been doing up against your goals and your don't-let-me list
Set up your mentor profile — goals, reality, and your own don't-let-me list
Diagnose PayPal integration issues by scanning your codebase, environment, and API usage patterns — then offer targeted fixes
Explain a PayPal API error code or message and provide actionable solutions
Show PayPal sandbox setup, credentials, and developer dashboard resources
Process delegation requests from agents and orchestrate multi-agent workflows.
Self-check the Gearbox installation and print a PASS/WARN/FAIL report
Creates a project-local copy of the Gearbox routing policy. Optional — only needed if you want to customize the policy for this repo.
Run a phantom user test session against a running web application.
Generate a draft story markdown from a story tracker or a feature description
Execute BDD test scenarios in a .feature file using browser automation. Use --record to generate a Playwright .spec.js file.
Export a pitch deck to PPTX, video, and/or speaker notes in one command.
Generate launch-video-style React presentations with shared-layout (FLIP) morph transitions. Subcommands: new, iterate, render, pptx, video, export. Use when…
Export the active morph-deck deck to PowerPoint .pptx with Morph transitions.
Check benchmark JSONL results and update success rates in benchmark-comparison.md
Story QA - multi-agent verification of a story implementation against its spec: per-AC verdicts, code reuse and design conformance, dead code, then adversarial…
Phase-gated refactoring/design loop - session-blind subagents build the map and traces, empirical probes precede the design, an approval gate guards…
Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observability, data/messaging/integration, generalist),…
Plan a new piece of work and add it to the lauren queue
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic