Ruling — Vagrantsong

You asked

How do I setup the game?

Answered counted as answered

Asked with: Vagrantsongbg-340325-en-1e

To set up the game, follow these steps:

1. Place the 27 Rummage Tokens from the Vagrantsong Box into the Bindle.[1]

2. Find the Tier 1 Junk cards on the back, shuffle them, and set them aside to create your starting Junk deck.[1]

3. Follow the specific setup instructions for your chosen Scenario in the Scenario Book, which may include placing Terrain, Markers, or Event Tokens in the Bindle and on the board, placing Vagrants in specific spaces, and placing the Threshold Marker according to the player count.[1]

4. Find the associated Ritual cards for the Scenario and place them face up near the train board.[1]

5. For the first Scenario ("Shelter from the Storm"), follow the specific setup instructions on page 1 of the Scenario Book.[1]

6. If the setup instructions for a Scenario state to place a Haint, place that Haint (the art for which can often be found on the bottom-left of the Scenario's first page).[1]

7. In the first Scenario, the final setup step is to flip to the Scenario's Event page, then read out loud and resolve the associated text.[1]

[1] RULEBOOK Vagrantsong — Rulebook · p.12 · Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1

Settled. Play 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 221 ms · ask 8088 ms · total 8311 ms
single-flight (PR-5): queued 0 ms · generation 8311 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 12, "score": 0.04918, "snippet": "Before you play, you will need to set up the train board! When setting the game up for the first time, place the 27 Rummage Tokens that come in the Vagrantsong Box into the Bindle. This is the default setup, and unless instructed otherwise you will return it to this state after every game. Many effe", "headingPath": "Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1", "sharpsignalDocId": 1162}, {"page": 31, "score": 0.032258, "snippet": "For this step, players are given multiple options and Actions that are unique to the Camp Phase that they can perform. Players will collaboratively make choices during this step. To start, players must determine how many Coins they have to spend! Each Vagrant who played in the previous Scenario adds", "headingPath": "1. SPEND COINS", "sharpsignalDocId": 1162}, {"page": 31, "score": 0.031746, "snippet": "During the very first Camp Phase, take all the Tier 1 Junk cards and shuffle them, then place the top Junk card from the deck near DC to represent the Junk he is offering during the Camp Phase. Vagrants will sometimes be instructed to add cards to the Junk deck. When this happens, shuffle the new Ti", "headingPath": "Setting Up the Junk Deck", "sharpsignalDocId": 1162}, {"page": 3, "score": 0.03125, "snippet": "Remember these when playing: 1. Rules on E vents, cards, and Scenarios supersede rules in this Rule Book. If these rules contradict one another , follow the rules on the Event first, then the card (such as an In-Between or Skill card), then the Scenario, and finally this Rule Book. 2. Whene ver play", "headingPath": "", "sharpsignalDocId": 1162}, {"page": 34, "score": 0.030769, "snippet": "Read and resolve the Victory or Defeat Moment, based on the previous Scenario's outcome. Tear Down the just completed Scenario. Each Vagrant restores their full Humanity (leave Wounded Skills and Broken Junk alone for now). Clean up the previous Scenario. Put away game components. Discard any Haint ", "headingPath": "Camp Phase Timing Chart", "sharpsignalDocId": 1162}, {"page": 34, "score": 0.030303, "snippet": "Below are two charts to help with timing during a round of play and the Camp Phase. Round begins! Move the Round Marker up one and any Events (or Tokens) on that space on the Round Track trigger. Then any 'beginning of round' special rules trigger. Vagrants decide together which Vagrant should perfo", "headingPath": "5. START NEXT SCENARIO · Round & Turn Order Timing Chart · 3.\t The Haint takes a turn.", "sharpsignalDocId": 1162}, {"page": 28, "score": 0.030159, "snippet": "Below is a step-by-step example of a round in a 2-player game. Here, we see the Revivalist and Cursebearer facing off against a dastardly Lost Soul . Don't worry, this example Scenario doesn't exist during the campaign, so reading this doesn't spoil anything! In this example, the Scenario has alread", "headingPath": "Example Round · 1. The Start of Round 4", "sharpsignalDocId": 1162}, {"page": 32, "score": 0.029851, "snippet": "During the Manage Vagrants step, players may also choose to play as a different Vagrant if they would like. To do so, first permanently discard any Exclusive Skills that you have learned as the Vagrant you no longer wish to play. Starting Skills are not permanently discarded this way and may be take", "headingPath": "Choosing a New Vagrant · Adding New Players", "sharpsignalDocId": 1162}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 12, "quote": null, "headingPath": "Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1", "sharpsignalDocId": 1162}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 1162 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1162 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 0.92255 of 878 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 24, 2026 08:44 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 Vagrantsong — Rulebook (corpus doc 1162)	Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1	p.12	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	1. SPEND COINS	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
#3	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	Setting Up the Junk Deck	p.31	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
#4	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)		p.3	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
#5	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	Camp Phase Timing Chart	p.34	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
#6	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	5. START NEXT SCENARIO · Round & Turn Order Timing Chart · 3. The Haint takes a turn.	p.34	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 Vagrantsong — Rulebook (corpus doc 1162)	Example Round · 1. The Start of Round 4	p.28	0.030159 (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 Vagrantsong — Rulebook (corpus doc 1162)	Choosing a New Vagrant · Adding New Players	p.32	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

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 80 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 Vagrantsong — Rulebook (corpus doc 1162)	Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1	p.12	#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 Vagrantsong — Rulebook (corpus doc 1162)	Moment 72 · Moment 73 · Moment 74	p.47	#48	0.009346 (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 Vagrantsong — Rulebook (corpus doc 1162)		p.3	#16	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
#4	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	Setting Up the Junk Deck	p.31	#3	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 Vagrantsong — Rulebook (corpus doc 1162)	The Haint's Turn · The Scenario Book · Haint Moods · The Mood Token	p.22	#19	0.012821 (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 Vagrantsong — Rulebook (corpus doc 1162)	Moment 84	p.48	#12	0.014493 (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 Vagrantsong — Rulebook (corpus doc 1162)		p.3	#43	0.009804 (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 Vagrantsong — Rulebook (corpus doc 1162)	Example Round · 1. The Start of Round 4	p.28	#7	0.030159 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Vagrantsong — Rulebook (corpus doc 1162)	Anatomy of a Scenario · Pack The Bindle · Create The Junk Deck · Setup According to the Scenario · Scenario Book Page 1	p.12	no quote on the wire

generation — timing and the path taken

timing split: retrieval 221 ms · first delta 6328 ms · total 8311 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 221 ms · ask 8088 ms · gateway work 8311 ms · total 8311 ms
tokens in (the prompt the answerer read): 2240
tokens out (what the answerer generated): 257
tok/sec: 133.3 tok/sec — 257 output tokens in 1.928 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s ago)
gateway schema (read from the running child): schema head 0042_definer_search_path (live revision not readable by this principal)
answerer host (measured by rulesage): reachable (for 60h, checked 2s 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 1092), 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.