factory-applicability-discovery

To show applicable governance rules before command execution, this mechanism enforces pre-action transparency by scanning active LAWs, technical rules, and instructions against runtime context. It emits a fixed-format roll-call block as the first user-facing message before any actions are taken.

Frontmatter filtering for AI agent workflow governance works by dynamically scanning all governance entries and filtering them based on the current command's runtime context. This includes command phase, project scope, change type, and active technology frameworks to exclude non-applicable entries with explicit reasoning.

Pre-action validation in governed SDLC workflows is a deterministic discovery process that mandates a full, transparent listing of all applicable governance entries before a command proceeds. It allows users to review and veto unexpected policies or defect prevention rules before code generation starts.

To detect mid-session drift when governance rules change, this approach computes a discovery hash of all scanned frontmatter. If governance entries are modified mid-session, the hash automatically triggers a re-roll-call before any further destructive actions are taken.

Yes, you can use this governance discovery process for a FastAPI backend-only feature change. When running an implement command, it lists all active security policies, Python-specific defect prevention rules, and applicable structural skills, letting you confirm the ruleset before proceeding.

Your AI agent executes commands under unreviewed rules without a roll-call because it lacks a deterministic, frontmatter-driven discovery process. Implementing pre-action transparency ensures a standardized, parseable output block is emitted as the very first message for immediate user review.