You asked
How do I set up the game?
Answered counted as answeredAsked with: Codenames: Picturesbg-198773-en-1e
1. Organize players into 2 teams of roughly the same size, with at least two players on each team [1]. 2. Each team chooses 1 player to be their spymaster; the rest are operatives [1]. 3. The orange and purple spymasters sit on the same side of the table, opposite their own operatives [1]. 4. Mix up the picture cards, choose 20 at random, and lay them out in a 5×4 grid, ensuring all cards are oriented the same way [1]. 5. Spymasters choose a random key card and slide it into the stand between them, oriented the same as the 5×4 grid of pictures [1]. 6. Put the 7 orange tiles in front of the orange spymaster and the 7 purple tiles in front of the purple spymaster [1]. 7. Place the 4 bystanders and 1 assassin in between [1]. 8. Identify the starting team using the triangles on the top and bottom of the key card [1]. 9. Give the double agent tile to the starting team, flipping it to their color and adding it to their tiles [1].
🔧 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 258 ms · ask 4659 ms · total 2138813 ms
- single-flight (PR-5)
- queued 2133886 ms · generation 4927 ms
- retrieval refs (raw)
- [{"page": 7, "score": 0.045805, "snippet": "Instead of a number, you can say your clue is unlimited. For example, tiny: unlimited . This allows your operatives to make as many guesses as they want, as long as they keep guessing right. Operatives do not know how many pictures were intended by the unlimited clue, but sometimes they can figure i", "headingPath": "UNLIMITED CLUE · Enhance your board game sessions! · CODENAMES PICTURES · A game by Vlaada Chvátil · ZERO CLUE", "sharpsignalDocId": 119}, {"page": 2, "score": 0.032787, "snippet": "Organize players into 2 teams of roughly the same size, with at least two players on each team. Each team chooses 1 player to be their spymaster. The rest are operatives. The orange and purple spymasters sit on the same side of the table, opposite their own operatives. Mix up the picture cards, choo", "headingPath": "SPLIT INTO 2 TEAMS. · CHOOSE SPYMASTERS AND OPERATIVES. · LAY OUT 20 RANDOM PICTURES. · SPYMASTERS DRAW A RANDOM KEY CARD. · SPYMASTERS TAKE THE TILES. · GIVE THE DOUBLE AGENT TO THE STARTING TEAM.", "sharpsignalDocId": 119}, {"page": 4, "score": 0.032258, "snippet": "The operatives should take a moment to discuss the clue. (Or, take a moment to think, if you are the only operative.) Then, one of the operatives must make a guess by touching one of the cards . The spymaster covers the picture with a tile matching the color shown on the key. If you guess a picture ", "headingPath": "THE OPERATIVES MAY MAKE MULTIPLE GUESSES.", "sharpsignalDocId": 119}, {"page": 8, "score": 0.031746, "snippet": "Learn more at www.codenamesgame.com Spymasters must keep a straight face. When the operatives discuss your clue, do not react to their misguided ideas. Do not reach for any tile until they have touched one of the picture cards. If they guess right by accident, act like that was what you intended all", "headingPath": "REMINDERS AND TIPS · COMBINE WITH CODENAMES · CODENAMES APP · COMBINE WITH DUET", "sharpsignalDocId": 119}, {"page": 5, "score": 0.03125, "snippet": "Three things can go wrong: If you guess an innocent bystander, your turn ends. If you guess the other team's picture, your turn ends, and you have helped the other team! If you guess the assassin, you immediately lose the game! If your turn does not end with a wrong guess, you can end it voluntarily", "headingPath": "A WRONG GUESS ENDS YOUR TURN. · YOU CHOOSE TO END YOUR TURN. · YOU USE THE 'PLUS ONE' RULE. · WHEN YOUR TURN ENDS, IT IS THE OTHER TEAM'S TURN.", "sharpsignalDocId": 119}, {"page": 6, "score": 0.030769, "snippet": "Spymasters are expected to give away no more information than one word and one number. Do not preface your clue with additional comments. 'I don't know if you will get this' is a fact that goes without saying. And 'I don't know if you will get this unless you've read The Hobbit ' reveals way too muc", "headingPath": "KEEP A STRAIGHT FACE", "sharpsignalDocId": 119}, {"page": 6, "score": 0.030303, "snippet": "Your clue should be one word , no hyphens, no spaces. If you don't know whether your clue is one word, ask the opposing spymaster. If the opposing spymaster allows it, the clue is valid. In Codenames: Pictures, all word play is allowed. So you can use knight to lead your teammates to a picture with ", "headingPath": "VALID CLUES", "sharpsignalDocId": 119}, {"page": 3, "score": 0.029851, "snippet": "PURPLE OPERATIVES 1 key card (from a deck of 60) 7 purple agents 1 assassin PURPLE SPYMASTER ONLY SPYMASTERS SEE THE KEY! The key card shows the secret identities of the 20 pictures. The ape with a helmet is orange. The sphinx is an innocent bystander. The ladybeetle is purple. The singing parrot is", "headingPath": "GIVE THE DOUBLE AGENT TO THE STARTING TEAM.", "sharpsignalDocId": 119}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "SPLIT INTO 2 TEAMS. · CHOOSE SPYMASTERS AND OPERATIVES. · LAY OUT 20 RANDOM PICTURES. · SPYMASTERS DRAW A RANDOM KEY CARD. · SPYMASTERS TAKE THE TILES. · GIVE THE DOUBLE AGENT TO THE STARTING TEAM.", "sharpsignalDocId": 119}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 119 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 119 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)
- debug row retained until
- Nov 6, 2026 14:46
retrieval — what the search arm returned
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 Codenames: Pictures — Rulebook (corpus doc 119) | UNLIMITED CLUE · Enhance your board game sessions! · CODENAMES PICTURES · A game by Vlaada Chvátil · ZERO CLUE | p.7 | 0.045805 (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 Codenames: Pictures — Rulebook (corpus doc 119) | SPLIT INTO 2 TEAMS. · CHOOSE SPYMASTERS AND OPERATIVES. · LAY OUT 20 RANDOM PICTURES. · SPYMASTERS DRAW A RANDOM KEY CARD. · SPYMASTERS TAKE THE TILES. · GIVE THE DOUBLE AGENT TO THE STARTING TEAM. | p.2 | 0.032787 (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 Codenames: Pictures — Rulebook (corpus doc 119) | THE OPERATIVES MAY MAKE MULTIPLE GUESSES. | 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 Codenames: Pictures — Rulebook (corpus doc 119) | REMINDERS AND TIPS · COMBINE WITH CODENAMES · CODENAMES APP · COMBINE WITH DUET | p.8 | 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 Codenames: Pictures — Rulebook (corpus doc 119) | A WRONG GUESS ENDS YOUR TURN. · YOU CHOOSE TO END YOUR TURN. · YOU USE THE 'PLUS ONE' RULE. · WHEN YOUR TURN ENDS, IT IS THE OTHER TEAM'S TURN. | p.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)) | 300 |
| #6 | RULEBOOK Codenames: Pictures — Rulebook (corpus doc 119) | KEEP A STRAIGHT FACE | p.6 | 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 Codenames: Pictures — Rulebook (corpus doc 119) | VALID CLUES | p.6 | 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 Codenames: Pictures — Rulebook (corpus doc 119) | GIVE THE DOUBLE AGENT TO THE STARTING TEAM. | p.3 | 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 |
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 Codenames: Pictures — Rulebook (corpus doc 119) | SPLIT INTO 2 TEAMS. · CHOOSE SPYMASTERS AND OPERATIVES. · LAY OUT 20 RANDOM PICTURES. · SPYMASTERS DRAW A RANDOM KEY CARD. · SPYMASTERS TAKE THE TILES. · GIVE THE DOUBLE AGENT TO THE STARTING TEAM. | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 258 ms · first delta 3062 ms · total 2138813 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 2133886 ms · retrieval 258 ms · ask 4659 ms · gateway work 4927 ms · total 2138813 ms
- tokens in (the prompt the answerer read)
- 3203
- tokens out (what the answerer generated)
- 249
- tok/sec
- 137.7 tok/sec — 249 output tokens in 1.808 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 26s 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 41), 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.