ontology-sync

# /ontology-sync — keep the vault in step with the code The vault under `docs/ontology/` (this repo's dogfood) — or the user's own vault when one is selected — is the **shared mental model** between the developer and the AI agent. When code grows or shifts, the vault has to follow, otherwise the graph drifts and stops being a useful map. This skill runs after a unit of code work (new feature, refactor, rename, notable cleanup) and produces the corresponding ontology updates so the human sees the change appear in their workbench. ## When to run **Run when**: - a new user-visible capability landed (login flow, checkout flow, …) - a new concrete element landed (jwt-token, indexeddb-adapter, sigma-canvas, …) - a domain was reshaped (auth → split into auth + session, …) - a slug-level rename happened in code that should mirror in the graph **Skip when**: - the change is a typo, comment tweak, or single-line style nudge - the change is purely test fixture / lint config / docs prose - a revert leaves the existing graph accurate; otherwise inspect its semantic delta ## Workflow The MCP server `ontology-atlas` (the compiled `ontology-atlas-mcp` binary inside the installed app, or `mcp/src/index.js` from a source checkout) is the primary path. Fall back to the source checkout CLI with `node <atlas-checkout>/cli/src/index.mjs add|import|validate ...` if MCP is unavailable in the current session. There is no npm-installed `ontology-atlas` command to assume. ### 1. Read what's alr...