Ruling — Escape: The Curse of the Temple

← Escape: The Curse of the Temple

You asked

How do the players complete the task in the ghost chamber?

Answered counted as answered

Asked with: Escape: The Curse of the Templebg-113294-en-1e

To complete the task in the ghost chamber, players must perform the following steps:

1. Once the chamber is discovered, stack 4 of the 6 task tiles face down inside the chamber.[1]

2. The first player to enter the chamber reveals the top tile.[1]

3. One or more adventurers inside the chamber must roll the distinctive combination of icons shown on that tile.[1]

4. Once those icons are rolled, remove that tile from the game and reveal the next one.[1]

5. Repeat this process until all 4 task tiles have been removed from the game.[1]

6. Additionally, players must force the ghost to return to the ghost chamber.[1]

7. Any player in the same chamber as the ghost can 'push' the ghost into an adjoining chamber by rolling two torches.[1]

8. The ghost must be moved through open entrances (not through walls) until it is inside the ghost chamber.[1]

9. The task is complete once the ghost is inside the ghost chamber.[1]

[1] RULEBOOK Escape: The Curse of the Temple — Rulebook · p.18 · Task chamber: · Ghost chamber:

🔧 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 121 ms · ask 4474 ms · total 4598 ms
single-flight (PR-5): queued 0 ms · generation 4598 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 18, "score": 0.04918, "snippet": "Once this chamber is discovered, the players stack 4 of the 6 task tiles face down inside this chamber. When an adventurer first enters this chamber, he reveals the top tile. Each tile shows a distinctive combination of icons that must be rolled by one or more adventurers who are inside this chamber", "headingPath": "Task chamber: · Ghost chamber:", "sharpsignalDocId": 775}, {"page": 17, "score": 0.04598, "snippet": "The quest chambers offer new challenges. Each chamber confronts you with a task that you must master before you can escape from the temple. At the start of the game, all players must agree on how challenging they want this adventure to be. The more quest chambers you include in the game, the more di", "headingPath": "Module 5: Quest chambers · Set-up modifications · The quest chambers in detail: · Altar chamber:", "sharpsignalDocId": 775}, {"page": 31, "score": 0.032258, "snippet": "In order to enter this chamber players have to roll 3 torches . Players can activate a gem and find a treasure in this chamber. Use this treasure to place your adventurer in an adjacent chamber. You can chose any adjacent chamber, even the diagonal ones. While you are standing in a chamber with open", "headingPath": "Narrow gauge: · Portal: · VOID RUNNER · TRICKSTER", "sharpsignalDocId": 775}, {"page": 25, "score": 0.031746, "snippet": "Activate the chamber by placing the blue sand timer on the sand timer icon. Each player must immediately place one die in this chamber. Each player now has 1 minute in which to enter this chamber; if they do, they immediately retrieve their one die. Any player who fails to retrieve their die in time", "headingPath": "Sacrifice chamber: · Torch chamber: · Lava chamber:", "sharpsignalDocId": 775}, {"page": 16, "score": 0.03125, "snippet": "5 Quest chambers 3 Quest markers 1 Ghost Altar chamber 12 Character cards - 2 cards for each character (1x permanent, 1x activatable) Doc Muscleman Discoverer Priest Mechanic Task chamber This expansion contains 2 new modules: Module 6: Characters You may use these modules individually, together, or", "headingPath": "Module 5: Quest chambers · Module 6: Characters", "sharpsignalDocId": 775}, {"page": 13, "score": 0.030769, "snippet": "Immediately after both the first and the second countdown, remove all discovered illusion chambers from the temple and place them on the bottom of the draw pile (example 1). This may result in gaps within the temple, so in order to continue exploring, the players must fill these gaps by discovering ", "headingPath": "Special features of the illusion chambers:", "sharpsignalDocId": 775}, {"page": 29, "score": 0.030303, "snippet": "You are not allowed to touch your adventurer figure, the draw pile or the gems on the gem depot. Better get some other player to help you move those pieces. QUEENIE: THE MAZE Only playable with the basic game. The rules of the basic game remain unchanged. 2 Chambers (1x mirage chamber, 1x gear chamb", "headingPath": "Mind control: · Game components and changes during set-up · Mirage chamber: · Gear chamber: · Pitfall: · Magical bond:", "sharpsignalDocId": 775}, {"page": 23, "score": 0.029412, "snippet": "The player lifts this chamber together with their adventurer and moves it clockwise around the temple without changing its orientation, testing each empty space adjacent to an existing tile in the temple until the entrance stairway on the moving platform connects to a door on another chamber in the ", "headingPath": "Moving platform: · Invocation chamber: · Cliff: · Slide trap:", "sharpsignalDocId": 775}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 18, "quote": null, "headingPath": "Task chamber: · Ghost chamber:", "sharpsignalDocId": 775}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 775 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 775 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 0.91293 of 758 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 13, 2026 17:55

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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Task chamber: · Ghost chamber:	p.18	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Module 5: Quest chambers · Set-up modifications · The quest chambers in detail: · Altar chamber:	p.17	0.04598 (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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Narrow gauge: · Portal: · VOID RUNNER · TRICKSTER	p.31	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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Sacrifice chamber: · Torch chamber: · Lava chamber:	p.25	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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Module 5: Quest chambers · Module 6: Characters	p.16	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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Special features of the illusion chambers:	p.13	0.030769 (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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Mind control: · Game components and changes during set-up · Mirage chamber: · Gear chamber: · Pitfall: · Magical bond:	p.29	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
#8	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Moving platform: · Invocation chamber: · Cliff: · Slide trap:	p.23	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 40 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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Task chamber: · Ghost chamber:	p.18	#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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Module 5: Quest chambers · Set-up modifications · The quest chambers in detail: · Altar chamber:	p.17	#2	0.04598 (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
#3	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Module 5: Quest chambers · Module 6: Characters	p.16	#5	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))	vector + the doc-priority boost arm	the re-ranker chose it
#4	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	The actions · 1. Enter a chamber · 2. Discover a chamber	p.7	#10	0.014286 (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
#5	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)		p.16	#30	0.011111 (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 Escape: The Curse of the Temple — Rulebook (corpus doc 775)	QUEENIE: QUEST CHAMBERS · Game components and changes during set-up · Chaos chamber: · Constellation chamber: · Snake pit:	p.28	#15	0.013333 (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
#7	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Tree of Life: · Obelisk chamber:	p.19	#13	0.013699 (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
#8	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Sacrifice chamber: · Torch chamber: · Lava chamber:	p.25	#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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Escape: The Curse of the Temple — Rulebook (corpus doc 775)	Task chamber: · Ghost chamber:	p.18	no quote on the wire

generation — timing and the path taken

timing split: retrieval 121 ms · first delta 2981 ms · total 4598 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 121 ms · ask 4474 ms · gateway work 4598 ms · total 4598 ms
tokens in (the prompt the answerer read): 2970
tokens out (what the answerer generated): 220
tok/sec: 140.2 tok/sec — 220 output tokens in 1.569 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 24s 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: 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 711), 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.