Ruling — Spirit Island

You asked

How do I setup the game?

Answered counted as answered

Asked with: Spirit Island: Branch & Clawbg-191831-en-1e

This game has a verified setup checklist. Every step is quote-checked against the rulebook, judged for entailment, and approved by a person — with honest holes wherever any of that failed.

Open the setup checklist for Spirit Island →

This checklist covers Spirit Island's rulebook. It does not cover Spirit Island: Branch & Claw.

approved Jul 13, 2026 · baked by gemma4:12b · prompt checklist-structurer-v3

If using the extension to the Invader Board: 1. Add the extension to the Invader Board [1]. 2. Put the Beasts, Wilds, Disease, and Strife tokens in the corresponding areas on the Invader Board extension [1]. 3. Shuffle the Event Deck and put it on the Events space on the Invader Board extension [1]. 4. During Setup, put one [token] and one [token] on each Island Board; the [token] goes in the lowest-numbered land with no printed Setup icons, and the [token] goes in land #2 (with the City) [1][2]. If playing with the thematic side of the Island Boards: 1. Place tokens as indicated by the Setup icons in each land [1][3].

[1] RULEBOOK Spirit Island: Branch & Claw — Rulebook · p.7 · SETUP CHANGES · SHORT ON SPACE?

[2] RULEBOOK Spirit Island: Branch & Claw — Rulebook · p.24 · TOKENS · AIDED BY · NEW TURN ORDER · Spirit Phase · Slow Power Phase (Cards and Innate) Time Passes

[3] RULEBOOK Spirit Island: Branch & Claw — Rulebook · p.17 · SOLO PLAY · THEMATIC MAP

Strategy guides → — community tips, kept separate from rulings

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 274 ms · ask 7391 ms · total 7675 ms
single-flight (PR-5): queued 0 ms · generation 7675 ms
retrieval refs (raw): [{"page": 17, "score": 0.032522, "snippet": "Blight Cards which have only 2 Blight per player on the Blighted Island side can be especially nasty when playing solo. If you get one of them in a single-player game, you may choose to draw a random replacement from among the unused Blight Cards. When setting up a game with the thematic side of the", "headingPath": "SOLO PLAY · THEMATIC MAP", "sharpsignalDocId": 220}, {"page": 7, "score": 0.016393, "snippet": "Add the extension to the Invader Board. Put the Beasts , Wilds , Disease , and Strife tokens in the corresponding areas on the Invader Board extension. Shuffle the Event Deck and put it on the Events space on the . . Invader Board extension. Playing with a Blight Card is now required . rather than o", "headingPath": "SETUP CHANGES · SHORT ON SPACE?", "sharpsignalDocId": 220}, {"page": 6, "score": 0.015873, "snippet": "Before adding this expansion to the base game of Spirit Island, make sure you've played Spirit Island at least a few times. The contents of this expansion add a ton of variety, thematic elements, and new ways to fight and frighten the Invaders, but it is truly not the best way to learn the game, as ", "headingPath": "BRANCH & CLAW", "sharpsignalDocId": 220}, {"page": 14, "score": 0.015625, "snippet": "RULES UPDATESRULES UPDATES VICTORY SPIRIT ISLAND PHASE ORDER EXPLORE BUILD RAVAGE DISCARD BLIGHT IF THERE IS EVER NO BLIGHT HERE, YOU LOSE THE GAME. per player PER PLAYER GENERATED FEAR SPIRIT PHASE Growth Gain Energy Choose Powers INVADER PHASE Blighted Island Fear Ravage Build Explore Advance Inva", "headingPath": "", "sharpsignalDocId": 220}, {"page": 21, "score": 0.015385, "snippet": "ADVERSARY & SCENARIOADVERSARY & SCENARIO SCENARIOS THE KINGDOM OF BRANDENBURG- PRUSSIA THE KINGDOM OF ENGLAND THE KINGDOM OF SWEDEN THE KINGDOM OF FRANCE DIFFICULTY 0 (NO CHANGE) BLITZ GUARD THE ISLE’S HEART SECOND WAVE (*) DIFFICULTY 1 POWERS LONG FORGOTTEN (**) BASE LEVEL BASE LEVEL BASE LEVEL DIF", "headingPath": "", "sharpsignalDocId": 220}, {"page": 14, "score": 0.015152, "snippet": "K D Y CARDS K ED Y CARDS ARD ARD PER PLAYER Some Fear and Event Cards may change the usual orderly progression of Invader Cards along the Invader Action Track, causing there to be multiple - or zero - cards on an Action Space. If there are no cards on an Action Space, you don't perform it, just like", "headingPath": "STRIFE EXAMPLES · MULTIPLE/MISSING INVADER CARDS", "sharpsignalDocId": 220}, {"page": 21, "score": 0.014925, "snippet": "| THE KINGDOM OF ENGLAND | THE KINGDOM OF SWEDEN | THE KINGDOM OF FRANCE | | BASE LEVEL | BASE LEVEL | | | | LEVEL 1 | BASE LEVEL | | LEVEL 1 | LEVEL 2 | LEVEL 1 | | LEVEL 2 | | | | | LEVEL 3 | LEVEL 2 | | LEVEL 3 | LEVEL 4 | | | LEVEL 4 | LEVEL 5 | LEVEL 3 | | | LEVEL 6 | LEVEL 4 | | LEVEL 5 | | LE", "headingPath": "ADVERSARY & SCENARIO", "sharpsignalDocId": 220}, {"page": 20, "score": 0.014706, "snippet": "| | | THE KINGDOM OF BRANDENBURG- PRUSSIA | | DIFFICULTY 1 | | THE KINGDOM OF BRANDENBURG- PRUSSIA | | | | BASE LEVEL | | DIFFICULTY 2 | | LEVEL 1 | | DIFFICULTY 3 | | LEVEL 1 | | DIFFICULTY 4 | DESTROYING FLAME DAHANINSURRECTION | LEVEL 2 | | DIFFICULTY 5 | DESTROYING FLAME DAHANINSURRECTION | LEVE", "headingPath": "DIFFICULTY CHART · USING THEMATIC MAPS WITH BRANCH & CLAW ADDS 1 TO THE DIFFICULTY.", "sharpsignalDocId": 220}]
citations (raw): [{"page": 7, "quote": null, "headingPath": "SETUP CHANGES · SHORT ON SPACE?", "sharpsignalDocId": 220}, {"page": 24, "quote": null, "headingPath": "TOKENS · AIDED BY · NEW TURN ORDER · Spirit Phase · Slow Power Phase (Cards and Innate) Time Passes", "sharpsignalDocId": 220}, {"page": 17, "quote": null, "headingPath": "SOLO PLAY · THEMATIC MAP", "sharpsignalDocId": 220}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; no base-rulebook boost — this ask EXCLUDED the base book, so its rulebook was never resolved and no id for it went on the wire (boosting it would have put that book back into a scope the reader took it out of); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
no base-rulebook boost — this ask EXCLUDED the base book, so its rulebook was never resolved and no id for it went on the wire (boosting it would have put that book back into a scope the reader took it out of)
layering — route: not layered — one pooled read, because one book was in scope and there is nothing to split
answered-before recall: this ruling was answered, so past rulings were not offered
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 3, 2026 20:59

retrieval — what the search arm returned

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the TWO-ARM fuse (full-text + vector), whose arithmetic ceiling is 0.03279 — both arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). Measured healthy band on this fuse: 0.016–0.033. 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 Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	SOLO PLAY · THEMATIC MAP	p.17	0.032522 (inside the measured healthy band 0.016–0.033)	300
#2	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	SETUP CHANGES · SHORT ON SPACE?	p.7	0.016393 (inside the measured healthy band 0.016–0.033)	300
#3	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	BRANCH & CLAW	p.6	0.015873 (below the measured healthy band (< 0.016) — a weak fuse)	300
#4	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)		p.14	0.015625 (below the measured healthy band (< 0.016) — a weak fuse)	300
#5	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)		p.21	0.015385 (below the measured healthy band (< 0.016) — a weak fuse)	300
#6	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	STRIFE EXAMPLES · MULTIPLE/MISSING INVADER CARDS	p.14	0.015152 (below the measured healthy band (< 0.016) — a weak fuse)	300
#7	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	ADVERSARY & SCENARIO	p.21	0.014925 (below the measured healthy band (< 0.016) — a weak fuse)	300
#8	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	DIFFICULTY CHART · USING THEMATIC MAPS WITH BRANCH & CLAW ADDS 1 TO THE DIFFICULTY.	p.20	0.014706 (below the measured healthy band (< 0.016) — a weak fuse)	300

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	SETUP CHANGES · SHORT ON SPACE?	p.7	no quote on the wire
[2]	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	TOKENS · AIDED BY · NEW TURN ORDER · Spirit Phase · Slow Power Phase (Cards and Innate) Time Passes	p.24	no quote on the wire
[3]	RULEBOOK Spirit Island: Branch & Claw — Rulebook (corpus doc 220)	SOLO PLAY · THEMATIC MAP	p.17	no quote on the wire

generation — timing and the path taken

timing split: retrieval 274 ms · first delta 6500 ms · total 7675 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 274 ms · ask 7391 ms · gateway work 7675 ms · total 7675 ms
tokens in (the prompt the answerer read): 2618
tokens out (what the answerer generated): 168
tok/sec: 150.8 tok/sec — 168 output tokens in 1.114 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 27s 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: ANSWERED — Answered
abstain rationale (n/a — this ruling answered): answered — no abstain rationale applies

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

decision: SERVED — setup-shaped and this game's approved setup checklist is offered above
pattern that matched: SETUP — "setup" / "set up"
matched words (in the normalized question): setup

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 7), 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.