claude-code-vault

Use when a question has a factual or best-practice answer but a single response might hallucinate, or when the user asks to "get consensus" or "sanity check this with multiple agents". Spawns N subagents on the same question with varied personas and tallies answer frequency.

Use when a question has real trade-offs and no single right answer: architecture choices, library selection, design direction. Runs a multi-round debate where agents see each other's positions across rounds, converge, and a synthesis is produced. For factual questions, use consensus instead.

Use when triaging an inbox: fetching unprocessed emails, classifying each into a label taxonomy, and applying labels via the provider's API. Provider-agnostic skeleton; scripts/label.py must be wired to your email provider before first use.

Use when a workflow built on an MCP server has stabilized and should become a production skill, or when the user says "convert this MCP workflow to a skill". Produces a skill with a bundled script that calls the underlying API directly, eliminating the per-session MCP token overhead.

Use when a PRD or spec exists and needs to become an executable backlog. Breaks the document into GitHub issues structured as vertical-slice tracer bullets, marks each as HITL or AFK, and files a final QA issue. Requires the gh CLI.

Use when implementing any task that should end in a commit. Encodes the definition of done: understand, implement with red-green-refactor for backend logic, run typecheck and tests until clean, then commit. Also the unit of work for autonomous loops.

Use when creating or revising any Claude Code skill, or when the user says "write me a skill for X". Encodes the house conventions: frontmatter style, body structure, when to bundle scripts, and project vs user scope.

Use when the user has a rough idea, feature request, or decision and the requirements are not yet pinned down. Interviews the user relentlessly, one question at a time, before any spec or code is written. Also use when asked to "grill me", "interrogate me", or write a PRD from a vague description.

Use when auditing a codebase before it goes public-facing, after a lab build, or on any periodic security pass. Checks secrets in code and history (including Claude Code transcripts), authorization and RLS, input validation, dependency red flags, and exposed endpoints.