toolproof / index / citerank|a masthead over nine indexes it did not buildmethodology 1.0 · CC-BY-4.0 · published by Compound Labs · read 13 Sept 2026 17:05 UTC
Nine indexes, one method9 of 9 answering, 1 behindAsk the nine
Sections

Nine indexes, one method

9 of 9 answering, 1 behind

9 indexes9 answering0 unreadable7 mint a badge2 deliberately not16 readings on 8 subjects751,973 listings read from source8.8% do not load

CiteRank markCiteRank

Whether answer engines cite a site when a buyer asks about its category.

On file, read on the capture date: obra/superpowers · anthropics/skills · n8n-io/n8n · anomalyco/opencode

the figure232answers recorded
engines answering5
free checks run25
as the index dates itmeasured 2026-09-12The index publishes a staleness flag and it is clear.
How it is testedthe index’s own sentence, as the read API returns it
CiteRank markCiteRankmeasuredmeasured 2026-09-12

A question is put to a live answer engine through a real browser and the answer it returns is recorded: one row per question per engine per run. Nothing is inferred from search rank; a citation counts when the engine actually produced it.

read from citerank.thecompound.tech/api/statsthe index itself, citerank.thecompound.tech

Measured 2026-09-12 by CiteRank. Read into this register 13 Sept 2026. Toolproof measured nothing here.

What it can be asked aboutnobody, and that is deliberate

CiteRank measures how often answer engines cite a site when a buyer asks about its category. That number moves for reasons its owner does not control, so a badge would be a scoreboard the embedder is losing. A badge is a thing a maintainer displays about themselves, and this is not one. The index is published in full.

Refusing to mint a badge that could only ever be used against its subject is the reason to trust the seven that are minted.

Why this index has no row on a repository8 subjects on file, all of them GitHub repositories

CiteRank answers about nobody by design, so there is no per-subject reading to hold. Its figures are above, its method is above them, and the index is published in full at its own address.

Four kinds of answer, kept apart: a reading, an index that answered and holds nothing, an index that did not answer, and an index that was never the right one to ask. Collapsing the fourth into the second would be a statement about a subject that nobody made.