craft-become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue,…
A command is the one you type. It runs exactly when you ask it to, and never before.
3,345 commands across 357 plugins.
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue,…
Convert a single HTML section or snippet into a registered WordPress block pattern PHP file.
Declare plugin dependencies and generate plugin-specific CSS and compatibility code for a block theme.
Convert a single HTML page into a WordPress FSE template (.html) in the theme's templates/ directory.
Asset inventory summary by surface type across managed environments
Build an asset lifecycle/aging report for a client from ScalePad Lifecycle Manager
Check whether the local Pi CLI is ready, show available models, and optionally toggle the stop-time review gate
Show active and recent Pi jobs for this repository, including review-gate status
Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope,…
SOC 2 compliance for Terraform — gap analysis, control implementation, evidence collection, and remediation guidance mapped to SOC 2 Trust Services Criteria.
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing…
Initialize Compound V in this project — detect backends and capabilities (Codex, Context7, required skills/agents), walk through any missing installs one at a…
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash; runs fully offline (FTS5, pure stdlib).…
Refresh the Compound V tier→model map — discover the concrete models each backend (claude, codex, antigravity, cursor, devin, opencode) currently offers, show…
Governance, Observability, Audit — autonomous infra-health observer for autonomous-dev itself. Subcommands: start | stop | status.
Validate all plugin components are working correctly (agents, hooks, commands)
Smart code implementation with full pipeline and batch modes
Deep understanding mode (nemawashi) - exhaustive context-gathering before action
Resume the latest Cursor chat (or a specific one) with an optional follow-up prompt.
Read-only code review of your git diff by a Cursor model. Reports findings; never edits files.
List Cursor chat sessions for this repository via `cursor-agent ls`.
Show project overview from the cix index — languages, top directories, key symbols
List a directory (one level) in an external cix project's server-side checkout
Query the claude-teams-brain for context about a specific role or topic
Store a persistent rule or convention that will be injected into all future teammates
Replay a past Agent Team session as a chronological narrative — who did what, what decisions were made, and what files were touched. Run `/brain-replay` to…
Show or set the agy (Antigravity / Gemini) model by writing ~/.gemini/antigravity-cli/settings.json — the reliable way to switch models (the unreliable --model…
Local NotebookLM over a FOLDER of documents using Antigravity (agy). Sweeps each document (PDF with text, scanned PDF, image, docx) into an objective-driven…
Ask a question over a notebook corpus you already built with /agy:notebook. agy answers from the per-document summaries…
Run the pre-write reuse gate before editing code. Give a natural-language change request, or pass --intent <file|-> for machine use.
Turn repo evidence into a kind, incremental refactoring plan. Usage: /lumin-repo-lens:refactor-plan [--root <repo>] [--output <dir>] [--profile quick|full]
First-touch guide for Lumin Repo Lens. Use when the user is new, unsure what to run, or wants a gentle explanation before reviewing repo structure.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic