Hold The Horde — Progress

Updated 2026-09-09 11:13 Jerusalem (UTC+3); current status through521. The owner resumed all project work and the original Claude roles in490. All work remains design only.

36 tracked design packages:34 preparation-closed,2 open (35 and36). Room32 and Encounter33 prepare24 modules/40 rooms, ten encounters INCLUDING two setpieces and thirteen major mechanisms;13 is not every interactive object or owner-approved game size. Player Information And Options34 closed509 at10:53:59, final61e0be4a (30,692 bytes). Global04 closed518 at11:07:24 after the accepted577236e7 continuity candidate and all eleven parent alignments were independently verified. Mechanical Interfaces And Opening Quantities35 was submitted515, received one critique520 and is in one author response521; Campaign Evidence And State Crosswalk36 is assigned519. PM519 now classifies all15 domains as usable first-pass contracts, with0 partial; this is not M3 completion. Interface, scope/handoff and coherence work remains. Intake407 and administration add no packages; these counts measure bounded written outcomes, not overall game completion.

“Closed” means the bounded written design/review outcome is complete. It does not mean a feature is implemented, every detail approved or fun validated. This board covers the current design batch; it is not a complete campaign or production backlog, and the closed/total ratio is not an overall game-completion percentage. Stable IDs stay fixed; added/reopened work must be recorded explicitly.

Actual availability and handoffs: owner490 resumed the original roles; verified identities, models and efforts are unchanged. Systems is WORKING on its one35 response521, with public receiving11:11:46 verified after one native send. The original Reviewer is STOPPED after critique520. Lead is WORKING36 under519: one courierd244533e delivered; hashcheck11:09:46, matching hash11:09:49, full contract11:09:51 and source read11:10:05 were verified. Lead’s eleven parents/Information34 and Systems’ continuity article remain STOPPED. No further04/34 reviews are pending. PM owns integration, intake and forecasts; routine forwarding needs no owner intervention.

Forward forecast — baseline F1

Adopted F1.14 forecast — 9 September: M3 first-pass wiki now targets 14 September (11–18 September), low confidence. M2 coherent core remains11 September (10–14); M4 detailed campaign remains10 November (20 October–1 December). Earlier published22 September remains in the history below. These are estimates, not deadlines guaranteed by team agreement.

All dates are2026; times are Jerusalem. Ranges are cumulative from8 September, not durations to add together. Baseline F1 was set8 September. Dates assume ordinary weekdays, about6–8 productive agent/PM operating hours per working day, functioning local hosts, and most consequential owner choices within a working day. That does not mean6–8hours of the owner's time or guaranteed overnight operation.

Will the full wiki be ready today? No. The adopted first-pass target is14 September (11–18 September), low confidence. The finite room/encounter inventories are prepared, while35/36, remaining cross-domain integration, scope/handoff and coherence remain. The later detailed-content milestone expands that design into the actual authored campaign. Neither milestone claims that a written plan has proved fun, balance, performance or30/90/100–200hours of play.

For M3, “complete first pass” includes the story's causal chain and ending structure; station layout/shifts/persistence; equipment acquisition and progression; combat/horde/trap families; oxygen/resources; rescue/colony/cast arcs; both language-learning arcs and clue distribution; journal, controls and accessibility; content budget, production constraints and the later validation plan. Numerical tuning can remain explicitly provisional. A major domain marked only “TBD” does not satisfy completion.

M4 has the weakest estimate because no approved content inventory yet exists. It assumes a substantial authored campaign matching the brief's ambition and two additional specialists. It is approximately30–60 active working days; with the current team alone, the initial audit estimated40–80. A smaller approved campaign could be much quicker; a dense secret/language campaign or a changed global rule could exceed the range. I will revise M4 after the inventory and three representative detailed content packages are written and checked. Final gameplay validation belongs to a separately authorised implementation/playtest phase; it has no honest calendar endpoint yet.

Estimated work timeline

This is a planning schedule, not historical delivery data. “Buffer” is allowed revision/decision time, not an unassigned promise to polish indefinitely.

The remaining critical sequence is35 mechanical/quantity disposition and36 evidence/state crosswalk → remaining actual-ID interface alignment → finite scope/handoff → one whole-v1 coherence disposition. Global04 and its eleven parents are now preparation-closed; prepared34 supplies the main information inventory. Packet preparation can proceed in parallel. Extra writers do not remove PM review and integration work.

Next delivery, Jerusalem: Mechanical Interfaces And Opening Quantities35 was submitted515 at 11:04:48, source a2d3c5e4… (38,858 bytes), and received its one critique520. Reviewer is STOPPED; Systems is WORKING on the one consolidated response521 after verified receiving11:11:46. The response targets 12:00 (11:30–12:30); reviewed preparation remains 13:00 (12:15–14:00) today9 September, low-medium confidence. Campaign Evidence And State Crosswalk36 was assigned519 at 11:09:24; Lead is WORKING after verified receiving/source reads11:09–11:10. Its draft targets 12:30 (12:00–13:30) and reviewed preparation 14:00 (13:00–15:30). Global04 closed518 at 11:07:24 after candidate577236e7 and all eleven parent revisions were independently verified; Lead has stopped those parents. Information34 closed509 at 10:53:59, final61e0be4a. M2, M3 and M4 targets remain unchanged. Room32 closed8Sep21:44:18;33 draft arrived8Sep21:57:56 and response22:12:33, before the owner paused all work. PM closed33 at9Sep10:32:09 after resumption; the overnight target was held, not missed by an unattended worker. The144–247 role-hour allowance is the dated8 September baseline, not measured labor or a current remaining balance.

Adopted F1.14 forecast — 9 September: M3 first-pass wiki now targets 14 September (11–18 September), low confidence. M2 coherent core remains11 September (10–14); M4 detailed campaign remains10 November (20 October–1 December). The revision follows the remaining-deliverables audit and preparation closeouts25–33, including the actual24-module/40-room and ten-encounter/thirteen-mechanism first passes. It uses current PM, Systems and restored original Lead/Reviewer capacity; additional agents are not prerequisites. It is a scope-based calendar judgment, not a conversion of word counts or elapsed chat minutes into role-hours. A changed joining architecture, expanded first-pass scope, unresolved integration or unavailable capacity can move the estimate. Next scheduled re-estimate:9 September18:00 Jerusalem, or sooner after consequential acceptance, scope or capacity changes. The earlier absent-two-specialists→25Sep scenario is historical and no longer the current schedule. The earlier14Sep conditional calculation in yesterday’s unpublished draft is now explicitly adopted by PM.

Extra agents — when and why

No extra agent creation is required today. Restored original Lead/Reviewer and existing Systems have substantive parallel assignments. Reconsider a technical/production specialist on10 September only if the concrete handoff queue needs independent expertise; campaign evidence integration is optional only for an actual unresolved gap.

These are design roles. No gamecode, prototypes, simulations, tests, purchases or AI art are authorised by this staffing plan. These additional sessions have not been created; setup is optional and capacity is counted only after independent onboarding, connectivity and a bounded assignment. PM will guide any needed setup one step at a time. Existing Systems retains its mechanical work; no new permanent critic is planned. Do not add writers when PM review/integration is the queue.

The original staffing proposal preceded accepted regional, language, story, cast, room and encounter inventories. Do not duplicate campaign maps or chains to occupy a role. Specialist absence no longer automatically implies a25 September wiki target; the adopted14 September estimate uses the restored existing team.

Why these estimates, and when they change

The revision follows the remaining-deliverables audit and preparation closeouts25–33, including the actual24-module/40-room and ten-encounter/thirteen-mechanism first passes. It uses current PM, Systems and restored original Lead/Reviewer capacity; additional agents are not prerequisites. It is a scope-based calendar judgment, not a conversion of word counts or elapsed chat minutes into role-hours. A changed joining architecture, expanded first-pass scope, unresolved integration or unavailable capacity can move the estimate. Historical early2–4/6–12/8–15/30–60-day allowances remain dated planning hypotheses; no new labor balance is inferred from them.

• Every15-minute report includes the next target/range and any movement. Next ordinary forecast review is9 September18:00 Jerusalem; update sooner when35/36 acceptance, remaining interface/handoff scope, owner answers or actual capacity changes the assumptions.
• Keep the original target visible when revising it. Record old estimate, new estimate and the concrete cause; do not silently move dates.
• A changed core mechanism or late owner story change may add roughly1–3 working days to the core/v1 forecast; quantify the actual affected work when it happens.
• A blocked decision moves its dependent work, not every parallel stream. Host outages are reported with elapsed delay. If authors produce a queue waiting over a working day for review/integration, reduce parallel intake before adding more agents.
• Forecasts must be useful even when confidence is low. Uncertainty is a reason to widen a range and state assumptions, not to omit an estimate or wait for certainty.

What changed in this report

• Combat And Enemy Roster27 preparation-closed443 at19:34, finalf1fe0d9a. One focused review/response corrected the new-role triggers and counterplay, staged cues for both regional orders, and Bellback's warning-start cone lock. Six ordinary/three special roles and two setpieces are prepared within ten encounter placements; exact populations, geometry, presentation and tuning remain later work.
• Home And Colony Loop28 preparation-closed450 at20:01:12, final5bff3436. One focused review/response clarified shared commissioning, first-return actions and each project's participants and lasting facilities. Five project briefs remain two reused/three new with three new fixed ship fixtures; cast choices, full scene scripts/state variants and management economy remain separate; Cast31 first-pass allocation is now prepared473.
• Two Language Discovery Map29 preparation-closed459 at20:23:52, finaldf0f48f5. One focused critique/response separated address/body evidence, retained valid captures across lives and supplied the iris variant's local B plate and completion state. Four proposed chains across two languages are prepared; actual clue/string/room variants and comprehension evidence remain unfinished.
• Story And Ending Map30 preparation-closed466 at20:42:22, final03c9cb8e. One focused critique/response separated current diagnostic evidence from historical chronology, specified evidence retained/lost before and after isolation, and used shared mechanical cycle impressions. Four mystery/personal chains and layered choices are prepared proposals; final story, departure rules and full cast/room/scene variants remain open.
• Cast And Short Rescue Map31 preparation-closed473 at21:12:44, final6456406b: five proposed people and fifteen unique first-pass scene briefs, three primary per person. One focused critique/response resolved the initial walked rescue route, actual movement event and first bench operation. D2 retains Dorn participating in the initial demonstrated operation; later commissioned use follows Home28. First-survivor/global mortality and final cast remain unselected.
• Station Room And Module Inventory32 preparation-closed481 at21:44:18, finald4ef2497(61009bytes):24modules/40rooms with explicit arrangement and compact-assembly constraints, retained conversion clues and independent core-isolation mechanism13. The13major units are not every interactive object and remain a proposed scope sample.
• Encounter And Mechanism Placement Inventory33 preparation-closed493 on9 September10:32:09, final5c1a9ad6. The one response plus narrow PM integration makes later E03 population a later-death-shift selection, preserves self-contained reset thresholds, and corrects Lens heat/cold and single-Cycler conservation. Ten encounters including two setpieces and thirteen major mechanism briefs are prepared; full variants and gameplay validation remain later.
• PM verified04's narrow legacy integration under441–443: Discovery Chain114e9267 and Expedition Proposal836ab2ae now use historical post-death routes and world-time capture/full frozen journal inspection. No new access guarantee was added; global04 remains open.
• PM closed narrow Coming Home/Home Projects compatibility456 at20:15:57, revisionsacbc945c/996d235a. Current Fork/supply, unloading, historical-route and refill rules align; PM owns both parents STOPPED. This adds no package and does not close global04.
• PM519 explicitly classifies15 usable first-pass domains and0 partial after global04 candidate and eleven-parent verification. This does not close M3:35 mechanical/quantity interfaces,36 evidence/state crosswalk, remaining actual-ID interfaces, scope/handoff and one coherence disposition remain. Full scripts and exhaustive states/layouts are M4; clusters are not extra numbered assignments.
• Global04 preparation closed518 at11:07:24 after Death Shift And Rescue Continuity candidate577236e7 and all eleven aligned parents were fully checked and independently read back. Lead retains STOPPED ownership of those parents; Systems retains STOPPED ownership of the new continuity article. Protected retreat and final station behavior remain explicit unselected owner branches; preparation closure is not owner adoption.
• Player Information And Options34 closed509 at61e0be4a:41 main states in9 bands,5 journal sections,4 manifest sections,10 options and4 walkthroughs. PM508 aligned recorded ship readings, essential target/readiness cues and the opening6→7→6 cargo example with4A.
• Mechanical Interfaces And Opening Quantities35 submitted515 at11:04:48, a2d3c5e4 (38,858 bytes), received one critique520; Systems WORKING on one response521, Reviewer STOPPED. Campaign Evidence And State Crosswalk36 assigned519 at11:09:24; Lead WORKING after verified receiving, covering existing8 chains/15 scenes without new campaign content.
• Five unanswered owner questions and unadopted intake407 remain. All original roles resumed490. M3 now targets14 September (11–18), low confidence; M2/M4 remain unchanged. The144–247 allowance remains dated. Yesterday’s F1.14 drafts were not published.

Open and closed outcomes

All milestone times below are Jerusalem time. “Updated” separates later owner-rule integration from the original preparation closeout.

Recent delivery timeline

These are observed calendar spans from assignment to preparation closeout, including handoffs and review. They are historical measurements, not estimates of labour or promised future turnaround.

Work sequence

The restored team has parallel authorized assignments. Assigned, sent, received, working and submitted remain distinct; a wiki post alone does not establish receiving activity. Lead retains STOPPED ownership after accepted alignment518 of these compatibility parents: Save And Content State; Connecting The Station; Rescue Rules; First Survivor; Cast And Short Rescue Map; Station Room And Module Inventory; Encounter And Mechanism Placement Inventory; First Expedition Options; Player Information; Death And Persistence; Shifting Station Options. All other article ownership remains unchanged; Information34 and the continuity article are STOPPED. Lead owns only new36 for current writing; Systems owns the one35 response521.

Decisions for the owner

Already answered: opening A and persistent room/group connections across shifts, culminating in connecting the entire station.

Open creative question: should completing the entire connection puzzle finally stabilise the layout, or should rooms keep moving while every established connection survives? PM recommends stabilisation as a reward for mastery. This is a proposed late payoff, not an answer inferred from the opening choice; the team can continue its comparison while it is pending.

The first-survivor choice is also already with the owner: Yeva, the pressure technician preserving ward measurements (PM recommendation), versus Aster, the supply clerk suspicious of the arrival and requesting one reversible door closure. Neither is selected. Progression, creature, story and corruption alternatives are prepared for later reactions; the owner is not expected to review the whole wiki at once.

Equipment acquisition question now with the owner: find working parts in station machines, accepting loss of their local function until the part is returned (PM recommendation), or study working examples and spend salvage to fabricate parts aboard. The reviewed acquisition proposal supports this comparison; starting gear, capacity and exact economy remain separate. Independent interface work can continue while the choice is pending.

New apparent-ending question now with the owner: show credits and allow continuing from before departure (PM recommendation), or make departure permanently end this save. The question is unanswered; neither continuation behavior nor permanent save closure is adopted. Together with final station-layout behavior, first survivor and equipment acquisition, this was the fourth question; rescue question485 below brings the current total to five.

New rescue question now with the owner (485): if the astronaut dies during an eligible short rescue, use a protected retreat that leaves the survivor alive and unsent in the prepared refuge before one shift, with spent supplies still spent and a new short route to find; or allow danger and prepare concrete injury/loss options for a later choice. The proposed protection is new and unselected. No answer is inferred; the earlier four questions remain pending, making five.

Reporting agreement

PM sends a compact report every15 minutes during authorized active work, plus meaningful completion, disagreement, blocker or decision updates. Owner pause suspends work/check-ins;490 explicitly resumed them. Reports include open/closed preparation counts, actual delivery/activity, next target/range, current v1 forecast and its changes. No page/message count or invented game-completion percentage substitutes for progress. The fallback requires the computer and apps to remain available.