Canonical-tag steering: the catalog read is the whole mechanism

Canonical-tag steering

The catalog read is the mechanism; warnings alone are not

The Shipped Assumption

Replicator's CMS shipped a warn-only canonical-tag design on its agent publishing surface: a tags_list tool whose description says to copy names exactly, plus advisory lint with did-you-mean suggestions. AO measured the assumption across a 40-tag fixture catalog and 36 drafting tasks.

Drift Is Structural

Without guidance, models NEVER matched exact canonical casing; 0/36 clean on all three tiers, so tag drift is structural, not sloppiness.

The Tool Is the Mechanism

With the tool present, every model consulted it unprompted in 36/36 cells and landed on-catalog topics canonical on the FIRST attempt (Claude tiers 24/24, including every near-collision trap like llm→LLMs and frontend→Front-End); zero warning rounds were needed. Warnings without the tool recovered only 7–24/36; the lint can fix slug variants but cannot supply a catalog it never showed.

One Honest Edge

One honest edge: given off-catalog topics, opus returned empty tag lists 12/12 rather than invent; defensible editorial caution the registered non-empty gate mis-scored, filed as a protocol lesson.

The Design Stands

The shipped design stands: keep tool and lint together, no hard gating needed.