You asked
How do I set up the game?
Answered counted as answered1. The starting player chooses a faction and takes its Faction board [1]. 2. In clockwise order, each other player takes one of the remaining Faction boards and chooses which side to use (alternatively, factions may be randomly assigned) [1]. 3. Put the Game board in the middle of the table and the Cult board next to it [2]. 4. For your first game, recommended factions are: 2 players: Witches (green) and Nomads (yellow); 3 players: Witches (green), Nomads (yellow), and Alchemists (black); 4 players: Witches (green), Nomads (yellow), Halflings (brown), and Mermaids (blue); 5 players: Witches (green), Nomads (yellow), Halflings (brown), Mermaids (blue), and Giants (red) [2]. 5. Distribute the recommended factions among the players [2]. 6. Take all tokens in your faction's color: Priests, Structures, Markers, and Bridges [2]. 7. Put 7 Priests and 3 Bridges next to your F/action board, forming your 'supply' [2]. 8. Put the Structures on the corresponding spaces on your Faction board [2]. 9. Distribute the 7 Markers of your color: place one on the leftmost space of the Shipping track (value 0) (except for Mermaids who start at value 1; Fakirs and Dwarves do not use this Marker), place one on the bottommost space of the Exchange track of your Faction board (except for Darklings), and place another on space 20 of the Victory point track on the Game board [2]. 10. Distribute the remaining 4 Markers on space 0 of each of the 4 Cult tracks on the Cult board [2]. 11. Move the corresponding Marker on the Cult board up one space for each Cult symbol shown on your Faction board (e.g., Nomads start on space 1 in the Cults of Fire and Earth; Halflings start on space 1 in the Cults of Earth and Air; Witches start on space 2 in the Cult of Air; Mermaids start on the space 2 in the Cult of Water) [3]. 12. Distribute a total of 12 Power tokens between Bowls I and II as indicated on your Faction board [3]. 13. Randomly select which Bonus cards and Scoring tiles to use [4]. 14. Shuffle the Scoring tiles and place them face-up on spaces 1-6, beginning with space 6 [4]. 15. If you draw a Scoring tile with a Spade on its left side for spaces 5 or 6, put it aside and draw another one instead (then shuffle the discarded tile back in) [4]. 16. Cover the right half of the Scoring tile on space 6 with the Game end token [4]. 17. Shuffle the 9 Bonus cards and randomly draw the required number based on player count: 2 players (5 cards), 3 players (6 cards), 4 players (7 cards), or 5 players (8 cards) [4]. 18. Place the drawn Bonus cards face-up next to one another [4].
🔧 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 254 ms · ask 11279 ms · total 11546 ms
- single-flight (PR-5)
- queued 0 ms · generation 11546 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.032522, "snippet": "The Bonus cards and setup for a 2-player game. The Bonus cards and setup for a 5-player game. The Bonus cards and setup for a 3-player game. Note: Each faction (but one) has two special abilities: one from the beginning of the game on, the other one once its Stronghold has been built. These abilitie", "headingPath": "gAme And cult boArd · CHANGES IN THE MAIN GAME · scoring tiles · bonus cArds", "sharpsignalDocId": 161}, {"page": 6, "score": 0.032266, "snippet": "The Starting player chooses a faction and takes its Faction board . In clockwise order, each other player takes one of the remaining Faction boards and chooses which side to use. Note: Alternatively, randomly assign the factions. (Take one Dwelling of each color and randomly distribute them among th", "headingPath": "choosing A fAction boArd", "sharpsignalDocId": 161}, {"page": 4, "score": 0.03125, "snippet": "This section consists of two parts. For your first play, please follow the instructions of the static introductory game. Add the changes for the variable main game in your second play at the earliest. Put the Game board in the middle of the table and the Cult board next to it. For your first game, w", "headingPath": "SETUP · Assignment of fActions · components in fAction colors · fAction setup", "sharpsignalDocId": 161}, {"page": 5, "score": 0.031054, "snippet": "Your Faction board depicts some Cult symbols next to the starting resources. For each such symbol, move the corresponding Marker on the Cult board up one space . The Nomads (yellow) start on space 1 in the Cults of Fire and Earth, the Halflings (brown) start on space 1 in the Cults of Earth and Air,", "headingPath": "cult AdvAncements · bowls of power · gAme And cult boArd", "sharpsignalDocId": 161}, {"page": 20, "score": 0.029274, "snippet": "Ability: You start the game with only one Dwelling. You may only place this Dwelling after all the other players have build all of theirs (if necessary, after the Nomads have placed their third one, see setup on page 5) . You get 2 Favor tiles instead of 1 whenever you build a Temple or your Sanctua", "headingPath": "CHAOS MAGICIANS · GIANTS · FAKIRS · NOMADS · Magicians have placed their only Dwelling).", "sharpsignalDocId": 161}, {"page": 4, "score": 0.015873, "snippet": "Collect your starting resources. They are depicted at the top right corner of your Faction board, under your faction's name: Take the depicted resources and place them on your Faction board. (On top of these starting resources, you will get your income for the first round. See page 8.) The Witches g", "headingPath": "stArting resources", "sharpsignalDocId": 161}, {"page": 8, "score": 0.015385, "snippet": "Skip this section when reading for the first time. In the introductory game, the first Structures are placed on predefined spaces. Beginning with the Starting player and in clockwise order, place one of your Dwellings on an existing Home terrain . Then, beginning with the last player and in counterc", "headingPath": "plAcing the first structures · detAils · FLOW OF PLA Y OVER SIX ROUNDS · PHASE I : INCOME", "sharpsignalDocId": 161}, {"page": 14, "score": 0.015152, "snippet": "Each Special action may be taken only once per round . Special actions, like Power actions, are indicated by orange octagons and can be gained in a variety of ways. Some factions unlock a Special action when building their Stronghold . (These are explained in Appendix VI on page 20.) After building ", "headingPath": "7 - speciAl Actions · 8 - pAssing And new stArting plAyer", "sharpsignalDocId": 161}]
- citations (raw)
- [{"page": 6, "quote": null, "headingPath": "choosing A fAction boArd", "sharpsignalDocId": 161}, {"page": 4, "quote": null, "headingPath": "SETUP · Assignment of fActions · components in fAction colors · fAction setup", "sharpsignalDocId": 161}, {"page": 5, "quote": null, "headingPath": "cult AdvAncements · bowls of power · gAme And cult boArd", "sharpsignalDocId": 161}, {"page": 6, "quote": null, "headingPath": "gAme And cult boArd · CHANGES IN THE MAIN GAME · scoring tiles · bonus cArds", "sharpsignalDocId": 161}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- 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
- Oct 31, 2026 14:31
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 Terra Mystica — Rulebook (corpus doc 161) | gAme And cult boArd · CHANGES IN THE MAIN GAME · scoring tiles · bonus cArds | p.6 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | choosing A fAction boArd | p.6 | 0.032266 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | SETUP · Assignment of fActions · components in fAction colors · fAction setup | p.4 | 0.03125 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | cult AdvAncements · bowls of power · gAme And cult boArd | p.5 | 0.031054 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #5 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | CHAOS MAGICIANS · GIANTS · FAKIRS · NOMADS · Magicians have placed their only Dwelling). | p.20 | 0.029274 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #6 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | stArting resources | p.4 | 0.015873 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #7 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | plAcing the first structures · detAils · FLOW OF PLA Y OVER SIX ROUNDS · PHASE I : INCOME | p.8 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | 7 - speciAl Actions · 8 - pAssing And new stArting plAyer | p.14 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
chosen chunks — what the answer actually cited
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.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | choosing A fAction boArd | p.6 | no quote on the wire |
| [2] | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | SETUP · Assignment of fActions · components in fAction colors · fAction setup | p.4 | no quote on the wire |
| [3] | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | cult AdvAncements · bowls of power · gAme And cult boArd | p.5 | no quote on the wire |
| [4] | RULEBOOK Terra Mystica — Rulebook (corpus doc 161) | gAme And cult boArd · CHANGES IN THE MAIN GAME · scoring tiles · bonus cArds | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 254 ms · first delta 6768 ms · total 11546 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 254 ms · ask 11279 ms · gateway work 11546 ms · total 11546 ms
- tokens in (the prompt the answerer read)
- 3642
- tokens out (what the answerer generated)
- 703
- tok/sec
- 148.9 tok/sec — 703 output tokens in 4.722 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 83), 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.