Ruling — KeyForge: Call of the Archons

← KeyForge: Call of the Archons

You asked

How do I setup the game?

Answered counted as answered

Asked with: KeyForge: Call of the Archonsbg-257501-en-1e

To set up the game, perform the following steps, in order:

1. Place all damage tokens, Æmber tokens, and status cards in a common supply within easy reach of both players.[1]

2. Each player places their identity card to the left or right side of their play area.[1]

3. Each player places three key tokens, one of each color, with the unforged side faceup near their identity card.[1]

4. Randomly determine who is the first player; that player takes the first turn when the game begins.[1]

5. Each player shuffles their deck and offers it to the opponent for additional shuffling and/or a final cut.[1]

6. The first player draws a starting hand of seven cards, and the other player draws a starting hand of six cards.[1]

7. Each player, starting with the first player, has one opportunity to mulligan their starting hand by shuffling it back into their deck and drawing a new starting hand with one fewer card in it (this step is skipped in the Quickstart game).[1]

[1] RULEBOOK KeyForge: Call of the Archons — Rulebook · p.3 · KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP

Rule found, game on.

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live,vps
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 213 ms · ask 3957 ms · total 4173 ms
single-flight (PR-5): queued 0 ms · generation 4173 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 3, "score": 0.04918, "snippet": "This section introduces a number of foundational concepts to keep in mind while playing the game. If the text of a card directly contradicts the text of the rules, the text of the card takes precedence. During the game, players use their cards to collect Æmber. Players use Æmber to forge keys. The g", "headingPath": "KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP", "sharpsignalDocId": 734}, {"page": 2, "score": 0.046898, "snippet": "If you have never played a game of KeyForge before, start by using the Quickstart document included in the starter set to learn the basics of the game. After playing a game using the Quickstart, players can read the full rules in this document and learn more about the KeyForge setting. In addition t", "headingPath": "USING THIS DOCUMENT · STARTER SET COMPONENTS", "sharpsignalDocId": 734}, {"page": 4, "score": 0.032258, "snippet": "The game is played over a series of turns. Players alternate taking turns until one player wins the game. Each turn consists of five steps: 1 Forge a key. 2 Choose a house. 3 Play, discard, and use cards of the chosen house. 4 Ready cards. 5 Draw cards. The player taking a turn is referred to as the", "headingPath": "TURN SEQUENCE · STEP 1: FORGE A KEY · STEP 2: CHOOSE A HOUSE", "sharpsignalDocId": 734}, {"page": 4, "score": 0.031746, "snippet": "4 KEYFORGE RULEBOOK SUGGESTED PLAY AREA (MID-GAME) STEP 2: CHOOSE A HOUSE Each KeyForge deck is composed of three different houses, which are shown on the identity card. During this step, the active player chooses one of those three houses to activate, making it the active house for the remainder of", "headingPath": "", "sharpsignalDocId": 734}, {"page": 6, "score": 0.03125, "snippet": "Creatures enter play exhausted and are placed in the front row of the active player's play area. This row is referred to as the battleline. Creatures remain in play from turn to turn, and they each have power and armor values that they use to resolve fights, which are described later. Each time a cr", "headingPath": "CREATURES · UPGRADES · DISCARDING CARDS · USING CARDS · USING ARTIFACTS", "sharpsignalDocId": 734}, {"page": 5, "score": 0.030303, "snippet": "The active player may play or discard any number of cards of the active house from their hand and may use any number of cards of the active house that are in play under their control. Eligible cards may be played, used, or discarded in any order. A card's house is determined by an icon in the upper-", "headingPath": "STEP 3: PLAY, DISCARD, AND USE CARDS OF THE CHOSEN HOUSE · PLAYING CARDS · ÆMBER BONUS · PLAY ABILITIES · ITEM Ready and fight with a friendly CARD TYPES · ACTION CARDS · …", "sharpsignalDocId": 734}, {"page": 6, "score": 0.029851, "snippet": "6 KEYFORGE RULEBOOK UPGRADES Upgrades enter play attached to (i.e., partially overlapped by) a creature chosen by the player who controls the upgrade. Each upgrade remains in play from turn to turn and modifies the card to which it is attached. If the card to which an upgrade is attached leaves play", "headingPath": "", "sharpsignalDocId": 734}, {"page": 5, "score": 0.029412, "snippet": "The active player draws cards from the top of their deck until they have six cards in their hand. After a player completes this step, their turn ends. If the active player has more than six cards in hand, they do not discard down to six. If a player needs to draw cards (during this step or at any ot", "headingPath": "STEP 5: DRAW CARDS", "sharpsignalDocId": 734}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 3, "quote": null, "headingPath": "KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP", "sharpsignalDocId": 734}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 734 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 734 boosted
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)
answer fence: passed — letter density 0.92956 of 795 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Sep 15, 2026 23:31 UTC

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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP	p.3	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	USING THIS DOCUMENT · STARTER SET COMPONENTS	p.2	0.046898 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	TURN SEQUENCE · STEP 1: FORGE A KEY · STEP 2: CHOOSE A HOUSE	p.4	0.032258 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)		p.4	0.031746 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	CREATURES · UPGRADES · DISCARDING CARDS · USING CARDS · USING ARTIFACTS	p.6	0.03125 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	STEP 3: PLAY, DISCARD, AND USE CARDS OF THE CHOSEN HOUSE · PLAYING CARDS · ÆMBER BONUS · PLAY ABILITIES · ITEM Ready and fight with a friendly CARD TYPES · ACTION CARDS · …	p.5	0.030303 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)		p.6	0.029851 (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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	STEP 5: DRAW CARDS	p.5	0.029412 (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 60 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 KeyForge: Call of the Archons — Rulebook (corpus doc 734)	KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP	p.3	#1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	MOST POWERFUL · MULLIGAN · NEIGHBOR · OMNI · OFF HOUSE · OPPOSING · …	p.11	#33	0.010753 (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
#3	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	USING THIS DOCUMENT · STARTER SET COMPONENTS	p.2	#2	0.046898 (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
#4	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)		p.4	#4	0.031746 (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 + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	FLANK · FORGE · FRIENDLY · HAZARDOUS (X) · HEAL · HOUSE CHOICE · …	p.10	#14	0.013889 (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
#6	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	CHAINS · CHAIN HANDICAPS (OPTIONAL) · SUGGESTIONS FOR ASSIGNING CHAINS	p.8	#10	0.02782 (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
#7	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	STEP 5: DRAW CARDS	p.5	#8	0.029412 (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 + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	TURN SEQUENCE · STEP 1: FORGE A KEY · STEP 2: CHOOSE A HOUSE	p.4	#3	0.032258 (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 + the doc-priority boost arm	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK KeyForge: Call of the Archons — Rulebook (corpus doc 734)	KEY CONCEPTS · THE GOLDEN RULE · OBJECTIVE · READY AND EXHAUSTED · RUNNING OUT OF TOKENS OR STATUS CARDS · GAME SETUP	p.3	no quote on the wire

generation — timing and the path taken

timing split: retrieval 213 ms · first delta 2941 ms · total 4173 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 213 ms · ask 3957 ms · gateway work 4173 ms · total 4173 ms
tokens in (the prompt the answerer read): 3656
tokens out (what the answerer generated): 228
tok/sec: 200.7 tok/sec — 228 output tokens in 1.136 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 7s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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): setup

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 668), 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.