Ruling — Mansions of Madness

← Mansions of Madness

You asked

How do I play?

Answered counted as answered

Asked with: Mansions of Madnessbg-83330-en-1e

To play Mansions of Madness, follow these steps:

General Setup

1. Choose a story from the five available options.[1]

2. Decide who will be the keeper (the antagonist) and who will be the investigators.[1]

3. Ensure each monster figure has a matching monster token in its base and place them within reach of the keeper.[1]

4. Sort all other markers and tokens into piles by type and place them within reach of all players, placing puzzle pieces in five facedown piles separated by their common backs.[1]

5. Investigator players take all Trait, Starting Item, and Investigator Character cards.[1]

6. The keeper player takes all Mythos, Exploration, Lock, Obstacle, Objective, and Keeper Action cards.[1]

7. The keeper builds the story's Event deck by placing the stage 'V' Event card on the bottom and ending with the stage 'I' Event card on top, without looking at the faces of the cards.[1]

8. Separate all other cards by their backs, placing Combat and Trauma decks near the keeper and the four Spell decks near the investigators.[1]

Investigator and Keeper Setup

1. Perform investigator and keeper setup simultaneously.[2]

2. Investigators follow steps in the chosen story's Investigator Guide, which include setting up the map, reading the introduction, and choosing investigators.[2]

3. Once an investigator is chosen, the player receives the corresponding Character card, Trait cards, and skill point tokens.[2]

4. Each investigator player chooses two Trait cards to represent abilities, receives the Starting Item or Spell card listed on those cards, and returns the other Trait cards to the box.[2]

5. Each investigator places their figure on the Start space.[2]

6. The keeper follows steps in the chosen story's keeper guide, which include choosing an objective and setting up Keeper Action cards, the Mythos deck, and seeding the board with Exploration, Obstacle, and Lock cards.[2]

Gameplay

1. The game is played over a number of rounds.[2]

2. During each round, players resolve their turns starting with the investigators.[2]

3. Investigators decide as a group the order in which they act; if they cannot agree, they proceed clockwise starting with the player to the left of the keeper.[2]

4. Each investigator completes their entire turn before the next player begins.[2]

5. Investigators win or lose as a team by attempting to find clues to reveal the Objective card and stop the keeper's plot.[3]

6. The keeper wins by fulfilling an evil scheme, such as driving investigators insane or bringing about the end of the world.[3]

7. The first side to complete their objective wins the game.[3]

[1] RULEBOOK Mansions of Madness — Rulebook · p.5 · General Setup

[2] RULEBOOK Mansions of Madness — Rulebook · p.6 · Investigator Setup · Keeper Setup · Playing the Game

[3] RULEBOOK Mansions of Madness — Rulebook · p.2 · Game Overview · Object of the Game

One rule clearer, zero feelings hurt.

🔧 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 199 ms · ask 5408 ms · total 5611 ms
single-flight (PR-5): queued 0 ms · generation 5611 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 18, "score": 0.046676, "snippet": "When attempting a puzzle, the player receives a number of puzzle actions equal to his investigator's Intellect (found on his chosen Trait card). With each of these puzzle actions, he may perform one of the following: Swap · a puzzle piece with an adjacent puzzle piece (see diagram on page 19). The p", "headingPath": "Attempting a Puzzle", "sharpsignalDocId": 625}, {"page": 6, "score": 0.046671, "snippet": "After finishing General Setup, the investigator players perform the steps listed in the chosen story in the Investigator Guide (at the end of this rulebook). These steps include setting up the game map, reading the introductory story, and choosing investigators. Once a player has chosen his investig", "headingPath": "Investigator Setup · Keeper Setup · Playing the Game", "sharpsignalDocId": 625}, {"page": 5, "score": 0.045476, "snippet": "Before playing the game, players must perform the following steps: Choose Story: 1. Mansions of Madness includes five unique stories, each with many possible card setups and three different endings. Before playing, players decide which of the five stories they wish to play during this game session. ", "headingPath": "General Setup", "sharpsignalDocId": 625}, {"page": 16, "score": 0.044388, "snippet": "Using a Spell card in this game is known as casting a spell. Most players do not start with Spell cards, but may later gain Spell cards by reading (using the ability of) tome Exploration cards that they have discovered. Although only four types of Spell cards are included in this game, they each hav", "headingPath": "Casting Spells · Mythos Cards", "sharpsignalDocId": 625}, {"page": 17, "score": 0.032258, "snippet": "Occasionally, an investigator will encounter a card that requires him to 'solve a puzzle.' Puzzles, in general, exist to slow down investigators and to showcase the intelligence of investigators. By completing a puzzle, the investigator can proceed with the movement or exploration the puzzle was hin", "headingPath": "Puzzles · Types of Puzzles · Puzzle Setup", "sharpsignalDocId": 625}, {"page": 9, "score": 0.03125, "snippet": "During an investigator's turn, he may perform a single action. Since he only receives one Action Step, choosing what action to take is often the most important decision he needs to make on his turn. This section lists the possible investigator actions. Sometimes an investigator will want to travel m", "headingPath": "Action Step · Run Action · Card Ability Action · Drop Action · Attack Action", "sharpsignalDocId": 625}, {"page": 9, "score": 0.030769, "snippet": "The most common action that investigators perform on their turn is exploring a room. During setup, the keeper places facedown Exploration cards in every room on the game board. Investigators may reveal these cards by performing an explore action in the room. Important: An investigator may explore a ", "headingPath": "Explore Action", "sharpsignalDocId": 625}, {"page": 19, "score": 0.029412, "snippet": "While exploring a room, Jenny Barnes reveals an Obstacle card that requires her to attempt Wiring Puzzle #2A. After setting up the puzzle (see diagram on page 17), she may now attempt the puzzle as part of her explore action. Jenny has an Intellect of 4, so she has four puzzle actions. 1. She uses h", "headingPath": "Attempting a Puzzle Example", "sharpsignalDocId": 625}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 5, "quote": null, "headingPath": "General Setup", "sharpsignalDocId": 625}, {"page": 6, "quote": null, "headingPath": "Investigator Setup · Keeper Setup · Playing the Game", "sharpsignalDocId": 625}, {"page": 2, "quote": null, "headingPath": "Game Overview · Object of the Game", "sharpsignalDocId": 625}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 625 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 625 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 0.91936 of 2195 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 25, 2026 22:41 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 Mansions of Madness — Rulebook (corpus doc 625)	Attempting a Puzzle	p.18	0.046676 (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 Mansions of Madness — Rulebook (corpus doc 625)	Investigator Setup · Keeper Setup · Playing the Game	p.6	0.046671 (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 Mansions of Madness — Rulebook (corpus doc 625)	General Setup	p.5	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
#4	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Casting Spells · Mythos Cards	p.16	0.044388 (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 Mansions of Madness — Rulebook (corpus doc 625)	Puzzles · Types of Puzzles · Puzzle Setup	p.17	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
#6	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Action Step · Run Action · Card Ability Action · Drop Action · Attack Action	p.9	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
#7	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Explore Action	p.9	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
#8	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Attempting a Puzzle Example	p.19	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 55 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 Mansions of Madness — Rulebook (corpus doc 625)	General Setup	p.5	#3	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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Optional Rules · Puzzle Time Limit · Monster Skill Points · Alternate Game Length	p.26	#11	0.027921 (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 Mansions of Madness — Rulebook (corpus doc 625)	Players will usually not need to measure line of sight, as it is often quite obvious whether the target can be seen.	p.21	#35	0.011628 (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 Mansions of Madness — Rulebook (corpus doc 625)	Game Overview · Object of the Game	p.2	#32	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
#5	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Skill Points During a Puzzle · Puzzle Secrecy and Cheating	p.18	#30	0.013158 (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 Mansions of Madness — Rulebook (corpus doc 625)	Puzzles · Types of Puzzles · Puzzle Setup	p.17	#5	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
#7	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Investigator Setup · Keeper Setup · Playing the Game	p.6	#2	0.046671 (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 Mansions of Madness — Rulebook (corpus doc 625)	Attempting a Puzzle	p.18	#1	0.046676 (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
[1]	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	General Setup	p.5	no quote on the wire
[2]	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Investigator Setup · Keeper Setup · Playing the Game	p.6	no quote on the wire
[3]	RULEBOOK Mansions of Madness — Rulebook (corpus doc 625)	Game Overview · Object of the Game	p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 199 ms · first delta 2619 ms · total 5611 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 199 ms · ask 5408 ms · gateway work 5611 ms · total 5611 ms
tokens in (the prompt the answerer read): 3175
tokens out (what the answerer generated): 590
tok/sec: 201.7 tok/sec — 590 output tokens in 2.925 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 6s 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: 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 558), 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.