token-audit

# Token audit A skill for auditing design token architecture across whichever tiers are in use — typically primitives and semantics, with component tokens where the system uses them. Produces a structured report with severity-rated findings and a prioritised remediation list. ## Before you begin: verify references Before doing anything else, confirm that every file listed in this skill's frontmatter `references:` field exists at its relative path from this SKILL.md. If any are missing, stop — the install is incomplete. This usually means a third-party installer (for example `npx skills install`) flattened the skill into a standalone folder and dropped the repo-root `knowledge-notes/` directory this skill depends on. Tell the user to reinstall using a supported method from `1-INSTALL.md` (git clone, or the `.plugin` bundle in Cowork) and to run `verify-install.sh` from the install root to confirm the fix. Only proceed without the references if the user explicitly says to — and if they do, state clearly in your output that it was produced in degraded mode without the pack's reference material. ## Context This skill draws on the tiered token architecture model: primitives encode raw values, semantic tokens encode intent, and — where present — component tokens map intent to specific UI contexts. Not every system uses component tokens, and the absence of a component tier is not a finding. Most token debt accumulates when tiers blur — when component contexts reference primitiv...