Add Sprint 11 plan and lane prompts: prove the corner block, then the job sheet

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-17 16:44:11 +10:00
parent bb393566c5
commit f2fe5915c8
2 changed files with 102 additions and 0 deletions

View File

@ -568,3 +568,47 @@ everyone else's site work is already on disk waiting for it.
> Support site_02 as it lands: dressing adjustments, contact sheets, and a > 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 > 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. > says the site has no winnable line, moving the tree is yours.
---
---
# SPRINT 11 prompts (the corner block is mean, then the job sheet)
Same rules: own clone, own branch, rebase onto latest main FIRST. Read
THREADS' last [I] entry then SPRINT11.md.
## Lane A — Sprint 11
> You are Lane A on SHADES 3D, Sprint 11. Rebase onto main, read SPRINT11.md.
> Gate 1 rulings first (carport collateral number — E proposes $180 with
> reasoning in the asset; widen the Anchor.type enum D flagged; answer C's
> venturi-gap question). Then gate 2, the job sheet: each night gains client
> + brief + pay schedule as data; forecast card becomes the job sheet,
> aftermath becomes the invoice. No reputation system yet — one week, five
> jobs, the framing. Shepherd as always.
## Lane B — Sprint 11
> You are Lane B on SHADES 3D, Sprint 11. Rebase onto main, read SPRINT11.md.
> Fix site_audit's headless false-negative (your setWorld ask), run it on
> site_02 WITH the venturi, and post the winnable lines. If the funnel kills
> every $80 line, C drops the gain before E moves the tree. Then support A's
> pay schedule with numbers (what does a good night on each site actually
> bank — your audit already knows).
## Lane C — Sprint 11
> You are Lane C on SHADES 3D, Sprint 11. Rebase onto main, read SPRINT11.md.
> Reconcile the venturi with A (site ships axis 2.1/gain 1.5; you measured
> 1.08/1.35 — one exchange, one edit), tune the gain to B's audit verdict,
> and land per-night forecast lead on the job sheet (your forecastLines lead
> param, waiting two sprints).
## Lane D — Sprint 11
> You are Lane D on SHADES 3D, Sprint 11. Rebase onto main, read SPRINT11.md.
> Play site_02 cold at last — the carport traps should read tempting, the
> funnelled southerly should make the ladder trip the site's thesis. File
> feel notes in THREADS. Then playtest the job-sheet week as A lands it.
## Lane E — Sprint 11
> You are Lane E on SHADES 3D, Sprint 11. Rebase onto main, read SPRINT11.md.
> Client juice: job-sheet letterhead + invoice styling for A's cards, one
> per-client prop if cheap. Stand by on the tree-move if B's audit demands
> it (C's gain drop goes first).

58
SPRINT11.md Normal file
View File

@ -0,0 +1,58 @@
# SPRINT 11 — THE CORNER BLOCK IS MEAN, THEN THE JOB SHEET
*Sprint 10 delivered its headline: sites are data. Two yards load from JSON,
night 3 moves to the corner block, the ladder keys on mechanism not type, the
carport is a priced trap with its own wreck, and the fabric plumbing has an
end-to-end assert. 296/0/0. What's left on the site is TUNING and PROOF —
then the game grows its last missing organ: the job sheet.*
Read THREADS from the last [I] entry.
## Gate 1 — prove the corner block (the site seams, all short)
1. **C + A: reconcile the venturi.** Site JSON ships axis 2.1 / gain 1.5; C
measured storm_03b's post-change wind at 1.08 and proposed gain 1.35.
Either A oriented the gap differently (tell C the built angle, C matches)
or the numbers are placeholders (take C's). One THREADS exchange, one edit.
2. **B: fix site_audit's headless false-negative** (your setWorld ask — A is
reading THREADS), then run it on site_02 WITH the venturi. If no $80 line
survives the funnel, C drops the gain (their standing offer) before E
moves the tree.
3. **D: play site_02 cold** — third sprint waiting, now truly unblocked.
The carport traps should read tempting-not-buggy; the ladder trip through
a funnelled southerly is the site's whole thesis. Feel notes in THREADS.
4. **A: two small rulings** — the carport collateral number (E proposes $180
with reasoning in the asset; change the constant, not the asset) and the
Anchor.type enum widening D flagged (a carport typed 'post' silently joins
the sail-post family; typed 'carport' it breaks the contract — widen it).
## Gate 2 — THE JOB SHEET (A owns; the landscaper service arrives)
DESIGN.md's callout structure, minimum viable: the week becomes a JOB — a
client, a brief, and pay that reads like an invoice.
- Each night entry gains client + brief text ("the Hendersons want the
seedlings alive — they leave for Cairns Friday") and a pay schedule
(base + garden bonus + no-collateral bonus). The forecast card becomes the
job sheet; the aftermath becomes the invoice.
- Client flavor is data (site JSON or night entry), not code.
- Keep scope honest: no reputation system yet, no job select — one week, five
jobs, the framing. Sprint 12 decides if reputation/warranty (DESIGN.md's
consequence loop) is next.
**E**: client-facing juice — job-sheet letterhead, invoice styling, one
per-client prop if cheap (the Hendersons' kid's bike against the fence).
**C**: per-night forecast lead — the job sheet shows tomorrow's ± band
resolving (your forecastLines lead param has waited two sprints for this).
## Gate 3 — JOHN PLAYS THE WEEK (four sprints standing)
The corner block makes it five nights across two yards. `python3 server.py`,
play it with the mouse, three sentences in THREADS. Sprint 12's shape — more
sites vs reputation vs heatwave days — is genuinely undecidable without them.
```
gate 1: venturi reconciled · site_audit passes site_02 · D's notes filed ·
carport priced · enum widened
gate 2: five jobs with briefs and invoices; the week reads as a landscaper's
week, not a survival ladder
gate 3: John's three sentences
```