AGENTS.md instructions for Gladisintelligible706/vibe-driven-dev, covering agents.md — vibe driven dev, what vdd is, official source of truth, your job as a coding agent and installation behavior.
Run a structured, autopilot codebase audit against curated coding standards and produce an actionable remediation plan with sprint-based prioritization.
Recommend the best AI provider and model for a project based on its use case, performance needs, cost constraints, and current model availability via MCPs.
Automatically discover, recommend, and install external skills from the open skills ecosystem after user intent is captured. Orchestrates find-skills installation, discovery queries, scoring, and phased install planning.
Generate the essential project setup files (PRD, Logic, Structure, etc.) that move a project from design completion to a structured repository foundation ready for execution.
Scan a repository against curated coding standards and produce a structured audit report, issue set, refactor plan, and sprint-based remediation roadmap. Use when the user invokes /vibe.audit or asks to review the codebase against established rules. Operates in full autopilot mode from repository scan to sprint plan…
Evaluates raw reference material from the archive (e.g., imported JSON rules or standard guidelines) and extracts them into usable VDD skills, constraints, or rule sets. Safely promotes learning material to executable context.
Guide a non-technical user through the first project conversation using Intent Capture Popups, capture minimal intent, translate it into VDD state, and propose the next best step in plain language.
Expand a completed PRD into the full execution-readiness artifact package across 3 ordered layers with quality gates, post-PRD skill bootstrapping, and autopilot decision checkpoints.
Turn a validated blueprint into execution-ready technical detail, validation paths, and implementation constraints without pretending the project is already ready to ship.
Prepare a project for structured downstream execution by packaging the trusted context, visible assumptions, and active decisions into a clean Spec-Kit handoff.