Self-iterating autonomous loop where the main agent acts as a pure orchestrator, spawning isolated Implementor and Critic subagents in rounds until the artifact converges, an iteration cap is reached, or human escalation is needed. Domain-agnostic — works for code, documents, plans, designs, copy, specs, proposals, or anything with an iterable artifact and explicit acceptance criteria. Also addressable by the short alias "bvl".
Initialize the Engram memory system — creates configuration, memory files, and CLAUDE.md integration. Trigger when the user sets up persistent memory for a project, or when `.claude/memory-settings.json` is missing and a memory feature is requested.
Search and recall memories from the Engram files. Trigger when a topic may relate to past discussions, when the user references previous context, or when the user asks "do you remember…".
Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.
Display Engram memory system status — configuration, file sizes, entry counts, and health check. Trigger when the user asks about memory state, what's been remembered, or for diagnostics.
Manage the dynamic skill library. Initialize skill-library/ and SKILLUSE.md, add new skills, remove skills, edit existing skills, and list available skills. Use when the user wants to manage, create, or modify skills in the skill library.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Create new files in knowledge base with directory governance. Use when user wants to save, create, or add content. Reads RULE.md to understand directory purpose and follows specified rules. Recommends target directory based on content analysis.