Add Sprint 10 plan and lane prompts: sites are data

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-17 15:12:55 +10:00
parent 855106d37e
commit 63beec87a7
2 changed files with 107 additions and 0 deletions

View File

@ -523,3 +523,48 @@ THREADS' last [I] entry then SPRINT9.md.
> carport — anchor-poor on purpose; its personality is "nowhere to tie off".
> Deterministic factory, contact sheet, and pyrrhic-ending card support when
> A rules.
---
---
# SPRINT 10 prompts (sites are data)
Same rules: own clone, own branch, rebase onto latest main FIRST. Read
THREADS' last [I] entry then SPRINT10.md. Gate 1 is A's, uninterrupted —
everyone else's site work is already on disk waiting for it.
## Lane A — Sprint 10
> You are Lane A on SHADES 3D, Sprint 10. Rebase onto main, read SPRINT10.md.
> ONE headline, from day one: extract the yard into data/sites/backyard_01.json
> (world.js builds from data; byte-identical yard proven by the existing
> anchor tripwires and quad-band asserts), then author site_02_corner_block
> from the pieces already waiting (E's carport GLB, C's venturi schema — give
> C their two gap coordinates, D's work:"cloth"|"bracket" anchor field). The
> week gains a site per night; night 3 moves to the corner block. Nothing
> else until this lands.
## Lane B — Sprint 10
> You are Lane B on SHADES 3D, Sprint 10. Rebase onto main, read SPRINT10.md.
> Build tools/site_audit/ from your quad/coverage/afford sweep — one command,
> any site JSON, reports the winnable lines or names the blocking corner.
> Run it on site_02 the moment A's JSON exists; if there's no $80 line, tell
> E to move the tree (their standing offer). Answer C's porosity-into-
> gardenHailExposure question in THREADS.
## Lane C — Sprint 10
> You are Lane C on SHADES 3D, Sprint 10. Rebase onto main, read SPRINT10.md.
> Wire venturi from A's site JSON when it lands; decide the week's storm/site
> pairing so the corner block teaches the venturi (southerly on night 3?);
> land the porosity/gardenHailExposure one-liner if B says yes.
## Lane D — Sprint 10
> You are Lane D on SHADES 3D, Sprint 10. Rebase onto main, read SPRINT10.md.
> Land needsLadder on A's work-field (mechanism, not type — your own audit),
> then play site_02 cold and log feel notes. The carport traps should read
> tempting, not buggy.
## Lane E — Sprint 10
> You are Lane E on SHADES 3D, Sprint 10. Rebase onto main, read SPRINT10.md.
> Support site_02 as it lands: dressing adjustments, contact sheets, and a
> carport-collateral aftermath line/card if the trap earns one. If B's audit
> says the site has no winnable line, moving the tree is yours.

62
SPRINT10.md Normal file
View File

@ -0,0 +1,62 @@
# SPRINT 10 — SITES ARE DATA (instructions for Opus 4.8 lanes)
*Sprint 9 closed the balance book: the wild night has a CLEAN $80 win (porous
cloth · dd 0.40 · the four-post quad), fabric is a real choice that decides
one corner's life, the pyrrhic ending has a rule, a verdict and a card, and
the settled-at-entry guard finally measures the thing the words mean — with a
proof that it can fail. Three retractions were filed this sprint, all
graceful, all measured. The engineering culture is the co-star now.*
*What did NOT land, for the second sprint running, is A's site extraction —
the week ate Sprint 8, the pyrrhic ruling ate Sprint 9. Every other lane's
site work is DONE and waiting: E's carport trap, C's venturi, D's ladder-seam
spec, B's audit sweep. Sprint 10 has one headline and it's A's, uninterrupted.*
Read THREADS from the last [I] entry.
## Gate 1 — SITE EXTRACTION (A, from day one, nothing else first)
`data/sites/backyard_01.json`: anchors, bed, house line, trees, posts, shed,
gnome, dressing list — world.js BUILDS FROM DATA, byte-identical yard as the
assert of success (E's tripwires already pin the anchor positions; a.test's
quad-band asserts must pass unchanged). Then `site_02_corner_block.json`:
E's carport (anchor trap, ratings baked in the GLB), ONE tree, paling fences,
smaller bed, C's venturi list (their schema is in THREADS — answer their
"where's the gap?" question with two coordinates). Week gains `site` per
night; night 3 moves to the corner block.
Include D's field: anchors carry `work: "cloth" | "bracket"` (or your
spelling) so needsLadder keys on the actual mechanism — their audit showed
the carport silently disables the ladder otherwise, failing open.
## Gate 2 — site_02 is FAIR before it ships (B, then D)
**B**: `tools/site_audit/` — the quad/coverage/afford sweep as a one-command
tool (your own words: geometry decides winnability, audit at authoring time).
Run it on site_02 the moment A's JSON exists; post the winnable line(s) or
tell E to move the tree. Every future site runs this before landing.
**D**: land needsLadder on the new field; play site_02 cold; feel notes in
THREADS. The carport traps should read as tempting, not as bugs.
## Everyone else (small)
**C**: wire the venturi from site JSON once A lands the shape; storm/night
pairing for the corner block (does the southerly buster move to night 3 so
the venturi teaches?). Optional: gardenHailExposure reading sail.porosity
(your offered one-liner) — B said yes or no in THREADS first.
**E**: whatever site_02's dressing needs once it's in-game (fence lengths,
bed size), refreshed contact sheets, and the site_02 aftermath cards if the
carport collateral wants its own line ("you took the carport with you").
## Gate 3 — JOHN PLAYS THE WEEK (carried; the game is ready)
`python3 server.py` → play five nights with the mouse, through the real
buttons. Three sentences in THREADS. Sprint 11 (jobs, clients, pay — the
landscaper service proper) gets shaped by them.
```
gate 1: both sites load from JSON; backyard_01 byte-identical; night 3 is
the corner block
gate 2: site_audit says site_02 has a winnable line; D's cold playthrough
logged; needsLadder keyed on mechanism, not type
gate 3: John's three sentences
```