Ruling — Horizons of Spirit Island

You asked

How do I play?

Abstained — no grounded answer; closest passages below counted as honest abstain

Asked with: Horizons of Spirit Islandbg-367498-en-1e

I looked through Horizons of Spirit Island's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.

The closest rulebook passages are below — check them before ruling.

RULEBOOK Horizons of Spirit Island — Rulebook · p.10 · SEQUENCE OF PLAY

Each turn has the following phases: Spirit Phase Fast Power Phase Invader Phase Slow Power Phase Time Passes Players act simultaneously within each phase, conferring as they wish. Table talk is not just allowed; it's likely necessary for victory! For more information on how to play the game, check o

RULEBOOK Horizons of Spirit Island — Rulebook · p.8 · GAME SETUP

POWER CARDS Separately, shuffle the Minor Power Cards and the Major Power Cards, putting each deck to the side of the board, accessible to all players. Each player takes all Spirit Presence discs and Single-Turn Effect Markers of one color, then chooses a Spirit by taking a Spirit Panel and four Uni

RULEBOOK Horizons of Spirit Island — Rulebook · p.26

STREAMLINING GAMEPLAY • As you play Power Cards, put the required Energy on top of them. This will help you remember to pay for them. • When you resolve a Power Card, you can push it forward or turn it sideways to note that it has been used. Don’t discard it until the end of turn, as you may be maki

RULEBOOK Horizons of Spirit Island — Rulebook · p.13 · SEQUENCE OF PLAY · ADVANCE INVADER CARDS

Add an Explorer to every land of the shown type which either: Contains at least 1 Town or City; or Is adjacent to at least 1 Town, City, or Ocean. No matter how many sources are in or adjacent to an Explored land, you only add one Explorer. Explorers are added directly from the supply, not moved aro

RULEBOOK Horizons of Spirit Island — Rulebook · p.18

SPIRITS Each Spirit has: • A Spirit Panel with Growth, Presence Tracks, and Innate Powers; • Four Unique Power Cards. ANATOMY OF A SPIRIT PANEL 1. Spirit Name 2. Art: An image of this Spirit. 3. Backstory: The story and history of the Spirit. 4. Setup: Initial Presence placement and any special inst

🔧 debug — where this ruling came from

outcome

ABSTAINED — Abstained — no grounded answer; closest passages below

warm abstain

this ruling — W1 — generic warm abstain · receipt: none (generic)

corpus profile

live,vps

answerer pin (deploy-frozen, attribution only)

gemma4:26b think:false 5571076f3d70

timings

search 91 ms · ask 5781 ms · total 5875 ms

single-flight (PR-5)

queued 0 ms · generation 5875 ms

retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read

[{"page": 10, "score": 0.048387, "snippet": "Each turn has the following phases: Spirit Phase Fast Power Phase Invader Phase Slow Power Phase Time Passes Players act simultaneously within each phase, conferring as they wish. Table talk is not just allowed; it's likely necessary for victory! For more information on how to play the game, check o", "headingPath": "SEQUENCE OF PLAY", "sharpsignalDocId": 522}, {"page": 8, "score": 0.047712, "snippet": "POWER CARDS Separately, shuffle the Minor Power Cards and the Major Power Cards, putting each deck to the side of the board, accessible to all players. Each player takes all Spirit Presence discs and Single-Turn Effect Markers of one color, then chooses a Spirit by taking a Spirit Panel and four Uni", "headingPath": "GAME SETUP", "sharpsignalDocId": 522}, {"page": 26, "score": 0.045688, "snippet": "STREAMLINING GAMEPLAY • As you play Power Cards, put the required Energy on top of them. This will help you remember to pay for them. • When you resolve a Power Card, you can push it forward or turn it sideways to note that it has been used. Don’t discard it until the end of turn, as you may be maki", "headingPath": "", "sharpsignalDocId": 522}, {"page": 13, "score": 0.045536, "snippet": "Add an Explorer to every land of the shown type which either: Contains at least 1 Town or City; or Is adjacent to at least 1 Town, City, or Ocean. No matter how many sources are in or adjacent to an Explored land, you only add one Explorer. Explorers are added directly from the supply, not moved aro", "headingPath": "SEQUENCE OF PLAY · ADVANCE INVADER CARDS", "sharpsignalDocId": 522}, {"page": 18, "score": 0.045476, "snippet": "SPIRITS Each Spirit has: • A Spirit Panel with Growth, Presence Tracks, and Innate Powers; • Four Unique Power Cards. ANATOMY OF A SPIRIT PANEL 1. Spirit Name 2. Art: An image of this Spirit. 3. Backstory: The story and history of the Spirit. 4. Setup: Initial Presence placement and any special inst", "headingPath": "", "sharpsignalDocId": 522}, {"page": 26, "score": 0.043941, "snippet": "The game works either way (or anywhere between) but both extremes at the same table can cause frustration. Try to make sure everyone is on the same page regarding time taken. TIPS & TRICKSTIPS & TRICKS 25 WHOOPSWHOOPS Y ou suddenly realize that for the past 4 turns you’ve been using a Power Card on ", "headingPath": "", "sharpsignalDocId": 522}, {"page": 22, "score": 0.043427, "snippet": "From your hand, your discard, or (if you somehow gain a Major Power mid-turn) from your cards in play. It can even be the Major Power you just chose. If you Forget a Power Card from play, you immediately lose the Elements it provided, and if you haven’t used it yet, you don’t get to. If you already ", "headingPath": "", "sharpsignalDocId": 522}, {"page": 7, "score": 0.04104, "snippet": "The Island is made up of 2 or 3 'boards', depending on whether you're playing on the 2 player or 3 player side. Each Island board has 1 Ocean, and 2 of each land type on it: jungles, mountains, sands, and wetlands. Each individual land on each board has a number in it, acting as a helpful reference ", "headingPath": "GAMEBOARD AND ISLAND BOARDS", "sharpsignalDocId": 522}]

citations (raw) — what the answer cited, chosen from a retrieval this page cannot show

[]

boost provenance — errata + base rulebook (E2/E3)

no registered errata card matched this query; base rulebook doc 522 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 522 boosted

answered-before recall

no past answered ruling for this game matched closely enough

similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)

debug row retained until

Nov 15, 2026 08:07

retrieval — what the passage search returned

what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.

per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.

token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.

fused rank	document	heading	page	fused RRF score	snippet chars
#1	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	SEQUENCE OF PLAY	p.10	0.048387 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#2	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	GAME SETUP	p.8	0.047712 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#3	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.26	0.045688 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#4	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	SEQUENCE OF PLAY · ADVANCE INVADER CARDS	p.13	0.045536 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#5	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.18	0.045476 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#6	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.26	0.043941 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#7	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.22	0.043427 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#8	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	GAMEBOARD AND ISLAND BOARDS	p.7	0.04104 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300

what the answerer read — the passages it actually had in front of it

what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.

candidate pool: the answering read scored 71 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.

floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.

arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.

read at	document	heading	page	fused rank	fused RRF score	carried by	how it got its slot
#1	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.26	#3	0.045688 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.20	#12	0.027072 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text	the re-ranker chose it
#3	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	WHO DECIDES	p.10	#38	0.012658 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one))	vector	the re-ranker chose it
#4	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	INVADERS	p.19	#18	0.024098 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text	the re-ranker chose it
#5	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.26	#6	0.043941 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	GAME SETUP	p.8	#2	0.047712 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)		p.22	#7	0.043427 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Horizons of Spirit Island — Rulebook (corpus doc 522)	SEQUENCE OF PLAY	p.10	#1	0.048387 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	vector + full-text + the doc-priority boost arm	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars

generation — timing and the path taken

timing split: retrieval 91 ms · first delta 5779 ms · total 5875 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 0 ms · retrieval 91 ms · ask 5781 ms · gateway work 5875 ms · total 5875 ms
tokens in (the prompt the answerer read): 2950
tokens out (what the answerer generated): 9
tok/sec: 195.7 tok/sec — 9 output tokens in 0.046 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 36s ago)
stream path: streamed — the gateway pushed at least one accumulated draft
watchdog: first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
num_ctx · think posture: both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.

disposition

outcome: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped

setup-shape — why the checklist band did or didn't render

decision: NOT_SETUP_SHAPED — no setup-shape pattern matched this question

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 453), so "no registered errata card matched" above could never have matched one

Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.