| Owner | Current work | Deliverable / acceptance |

| --- | --- | --- |

| **Independent Critic + Naive Design Reader** | Review when the vision submission exists | Critic: does the described play deliver the stated identity, and what is its strongest contradiction? Reader: retell the game in ordinary language without the glossary; identify at most three consequential comprehension gaps. Neither consistent arithmetic nor attractive prose alone establishes a good game |

| **PM + Wiki Editor** | Make current direction and status clear | PM reviews the proposed vision and significant changes, explains the result to the owner, and accounts for cut/change dependencies. Editor labels superseded rules, preserves provenance and fixes navigation; do not silently resurrect historical rules as current. No replacement deck until the premise itself can be clearly explained |

**Quality gate:** a reader should be able to explain what they will do and why they might want to do it after reading the vision page alone. An easier return earned through understanding can be a payoff; do not force waits or a particular tool merely to satisfy a reviewer. More pages, saves, names or estimated hours are not the success measure. An hourly check may produce no edit.

No new opening prompt, replacement agent or routine owner relay is needed: the owner has already started the Visionary with its mandate. Schedules/receipt are not inferred from this page. Design only; all owner phase and asset constraints persist.

lookup found no existing Clarity task. One Clarity schedule was created and confirmed enabled with an

hourly recurrence. It reviews substantive changes and notifies only for significant comprehension

verdicts or actionable blockers. The existing review checkpoint is unchanged.

**2026-09-07 · External Game Critic · In review; PM owns acceptance.** [External Critique 2de127](/Hold%20The%20Flood/External%20Critique?revision=2de127) reviews [Brief 0fff74](/Hold%20The%20Flood/Brief?revision=0fff74) and [Campaign 0cafb9 §3.2](/Hold%20The%20Flood/Campaign?revision=0cafb9), with [World 7b8ad1](/Hold%20The%20Flood/World%20And%20Mystery?revision=7b8ad1), [Build Paths 6d6d1d](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=6d6d1d) and [shared rules 5322f4](/Hold%20The%20Flood/Mechanics/Power%20And%20Attraction?revision=5322f4). The Visionary-specific expedition remains due; the existing Lead scene is concrete enough for this scoped review.

**Verdict:** promising for players who want understanding machinery to change crowd survival and future routes. **One finding, X37:** the middle Tram return begins with Rail/pass open and stairs available, yet its featured Coil plan incurs combat and loses the harvested charge without a demonstrated advantage for the investigation. Compare against taking the stairs immediately; answer with an actual benefit or overlooked constraint, or use the quick reconnaissance here and demonstrate the costly build at a suitable existing intervention. Do not remove a free route or force a wait to exercise equipment. The finding is a design judgment about this scene's value evidence, not a validated optimal route or a rejection of Coil everywhere.

**Retain:** the corrected late return's earned ease, optional Siphon margin and persistent tram state. X35 stays closed; X36 is withdrawn because missing decision-row numbers do not materially affect the product. Lead/Visionary own the design response; PM owns disposition. Full reasoning, counterargument, sacrifice and verdict-change conditions are on the review page. Written review only; no development or player testing.

| Equipment | Siphon adjacency removal accepted; [122d38](/Hold%20The%20Flood/Equipment?revision=122d38) countersigns the simplified rule and explains the current catalogue | Keep cargo/converter sacrifice, three-charge yield, selected bank, overflow, leakage and shelter fitting. No further countersign requested for this delivered change; update only dependencies changed by subsequent vision work |

The Clarity scheduling blocker was resolved during this review and independently confirmed; no owner action remains on it. Existing asset gaps and scope adequacy remain unresolved. No replacement deck, new agent, purchase or development approval is requested. The next owner-facing creative step is a refuge consequence the player can picture, alongside a worthwhile combat choice.

**2026-09-07 · Equipment and Build Designer · In review; PM owns acceptance.** [Equipment 122d38](/Hold%20The%20Flood/Equipment?revision=122d38) now opens with the current eight-cell rack, distinguishes three build families from catalogue items, and answers Equipment’s part of Q52 without promoting the historical six-cell seed. It countersigns the Visionary’s Siphon simplification: choose any carried wet salvage bundle, preview and sacrifice it with the one-use converter, and send three charge to the shelter-selected battery. Adjacency is removed because, with shelter-only rearrangement, it mostly forced pre-packing rather than another route or machine decision; capacity, leakage, fuel, overflow and the lost bankable bundle remain costs.

[Build Paths f6f8ef](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=f6f8ef) records the same rule boundary and answers Colony [c56634](/Hold%20The%20Flood/Colony?revision=c56634): Campaign [0cafb9](/Hold%20The%20Flood/Campaign?revision=0cafb9)’s berth-supported alternative may issue Beacon + default empty Battery, not Beacon + Battery + Kit. Omit the issued Kit or acquire it from an authored field offer. The existing three-item approach C remains legal only under tooling, not simultaneously with berth support.

**Sources processed:** PMR008 [37fd94](/Hold%20The%20Flood/PM%20Reviews/PMR008?revision=37fd94), Brief [0fff74](/Hold%20The%20Flood/Brief?revision=0fff74), Inventory [810057](/Hold%20The%20Flood/Mechanics/Inventory%20And%20Charge?revision=810057), Utility [4ffa18](/Hold%20The%20Flood/Equipment/Utility%20Modules?revision=4ffa18), Visionary Build Paths [bbb314](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=bbb314), Colony [c56634](/Hold%20The%20Flood/Colony?revision=c56634), Campaign [0cafb9](/Hold%20The%20Flood/Campaign?revision=0cafb9), Design Review [265a09](/Hold%20The%20Flood/Design%20Review?revision=265a09) and current Wiki Conventions. This is a bounded written-design response: no catalogue expansion, implementation, simulation, playtest or asset action.

**2026-09-07 · [Review, specific corrections and exact revisions](/Hold%20the%20Flood/PM%20Reviews/PMR007).** This table is the current disposition; older dated tables below are evidence/history, not commands to repeat delivered work. The original PMU007 depth criteria remain the acceptance standard. Correct effects are agreed; whole-game acceptance is withheld. Source hashes and narrow review scopes are on PMR007, not inferred from task receipts.

| Task | Owner | Evidence-backed status | Next useful action |

| --- | --- | --- | --- |

| DES104 → DES105 | Existing Lead | Integration changes required at [Campaign 9366c8](/Hold%20The%20Flood/Campaign?revision=9366c8); canonical decisions credited at [contract 8644ea](/Hold%20The%20Flood/Mechanics/Power%20And%20Attraction?revision=8644ea) | Use **Tram** as the common first/changed/later-return case. Integrate EQP102/COL102/WLD104, legal issue and reachable evidence order. Correct seven-cell berth-supported start and decide one consistent initial Exchange permission state. No larger issue cap or new omnibus document |

| CAM102 / CAM103 | Campaign and District Designer, with Lead on current authored districts | Exchange changes required at [5bc625](/Hold%20The%20Flood/Districts/The%20Exchange?revision=5bc625); clearer baseline accounting credited at [Districts e1136a](/Hold%20The%20Flood/Districts?revision=e1136a), not duration accepted | PMR007 §1/2/5: correct Exchange dispatch, fuel/rack/expiry/retrieval ledger and bank start; Collector winch versus 2 s power; provide actual Tram apron/manual return/offers and 30 s crossing or reject that location. Merge/justify observation-only repeat trips before changing the count |

| CMB101 / CMB102 | Combat and Enemy Designer | Current effect table credited at [6129ea](/Hold%20The%20Flood/Mechanics/Combat?revision=6129ea); live-copy corrections still required | Remove §0.2 unresolved C2 paragraph, §6 Spark-stun/most-room clauses and old presentation count. Then countersign or revise EQP102's three approaches against targeting, press and pursuit; no readability/balance claim from role-count limits |

| EQP101 | Equipment and Build Designer | Effect/interface contribution accepted at [dc3aa2](/Hold%20The%20Flood/Equipment?revision=dc3aa2), with [Arc fc64bb](/Hold%20The%20Flood/Equipment/Arc?revision=fc64bb); newer Equipment r4 and Coil/Inventory/Utility mirrors scoped in PMR007 | Equipment r4 already retires its pending Cable/Spark requests; no redo. Collector mechanism stays Campaign-owned. No blanket catalogue/asset acceptance |

| EQP102 | Equipment and Build Designer | Accepted as a delivered contribution at [Build Paths 6bc3f7](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=6bc3f7); integration pending, not CMB102 acceptance | Carry three legal small-start approaches plus bundle → 3 charge → 30 s lure into DES105. Coordinate exact offers/ground with Campaign and targeting with Combat; reject an unsupported short crossing. Broader catalogue depth remains unproven |

| COL101 / COL102 | Colony and Progression Designer | COL101 targeted corrections accepted; COL102 two-path contribution accepted at [fe7d88](/Hold%20The%20Flood/Colony?revision=fe7d88), conditional on shared route/acquisition | Mirror D026: comparison joins base receiver, one assembly for tooling or berth. Match the integrated Tram case and Equipment's smaller-package revisit clarification. Equal investment opportunities are not guaranteed income; no hauling tax |

| WLD104 | World and Mystery Designer | In review — targeted changes required at [e99445](/Hold%20The%20Flood/World%20And%20Mystery?revision=e99445) | Reorder clue/action chain onto accessible Lock Flight → Tram → Exchange → Collector progression and actual returns; clarify independent evidence for harvesting. Fix grounded-run persistence row. Mirror D026; do not sell bank state already on free prelaunch board |

| REV104 → REV105 | Independent Design Critic | REV104 contribution accepted at [ce94e4](/Hold%20The%20Flood/Design%20Review?revision=ce94e4), with closure qualification | Verify Combat/World residual copies identified by PMR007. Keep Exchange 16–18 open until corrected. Review depth only against the actual combined DES105 revision; do not certify readiness from isolated countersigns |

| D025 / REF110 | Lead + Reference Researcher | [Asset Audit fa674c](/Reference/Asset%20Audit?revision=fa674c) received/reviewed as bounded source/licence report, not suitability acceptance | Distinguish located sources, style/pose/animation uncertainty, adaptation work and gaps. Engine-drawn cues are not zero authoring. Correct Campaign §10's stale none-located statement; no purchase/custom request yet |

| EXT102 / TRL / CLR102 | Existing review contributors | X33 response credited, positioning deferred; [X32 5f950c](/Hold%20The%20Flood/External%20Critique?revision=5f950c) substantively addressed by EQP102 in its scope; Clarity reports no open item | Reassess actual design argument, not citation counts. Cold owner-path read after DES105 exists; at most three consequential findings. No duplicate demand for already delivered independent review |

**D026:** provisional next-draft simplification on Brief; no owner approval implied. Reference comparisons are not launch quotas. Existing team is sufficient. A wiki assignment does not wake another chat. All work remains textual design/review: no game code, build, prototype, simulation, playtest or unapproved asset creation.

[Findings, evidence and bounded handoffs](/Hold%20the%20Flood/PM%20Reviews/PMR006). The seven-district campaign now has its first coherent skeleton, a shared mystery/power explanation and a content-backed baseline of 34 expeditions / 8.2 expedition hours plus separately listed optional material. That duration is a drafting hypothesis, not measured playtime or an owner-approved scope. World and Campaign corrections and Colony's structural contribution are accepted as delivered work; the complete design still requires integration.

Current blockers are specific: canonical Coil water power is 2 seconds while Combat/Equipment use 8; Spark stun differs between the shared contract and its enemy page; ordinary panel/Grounder persistence conflicts with the blanket reset text; Colony's immediate Stop effect conflicts with the gradual cascade; Campaign still advertises the withdrawn “slower” ending; asset burden alternates between three, six and eight enemy silhouettes. The independent critic has not reviewed Campaign r2. No additional agent, owner relay, asset approval or development work is needed for this writing pass.

**2026-09-07 UTC · Equipment and Build Designer:** Equipment's contribution to the joint EQP102/CMB102 handoff is submitted below. PM owns acceptance; this does not submit Combat's work or change EQP101's In review state. No other author's contribution or task status is removed.

**One objective, three strategies:** reach the Tram summit, copy its timetable, inspect the open pass toward the Exchange, and extract at the depot. Build Paths compares a one-cell Kit ride-and-cut plan, four-cell Coil/Insulation wet-yard control followed by the road, and a three-cell Beacon/Kit dark-tram launch diversion. Literal racks, small-package issue, empty-bank funding, pursuit/Heavy counterplay, the 100-second lure limit, retrieval capacity, manual return and failure choices are explicit. No whole-ascent stun or safe funding is claimed.

**Discovery and later change:** propose Siphon versus Kit in the existing summit stores. After Collector withholding removes the expected first charge source, a three-cell Beacon/Siphon/empty-bank set can burn one locally gathered bundle for three charge and at most thirty lit seconds; the free manual detour preserves that bundle. Campaign must place a useful short crossing and the depot side apron; these are written route requirements, not measured timing. Retain twelve first-catalogue entries, not a final ceiling: REF107/X32's within-district-variety challenge is answered with changed actions and opportunity costs, not combination counts.

**Cross-role response:** agree with Colony fe7d88 that Campaign 9366c8's berth-supported seven-cell departure violates issue rules. Prefer a legal small start with explicit field offers/shelter fitting if more gear is needed; do not increase the cap or combine berth support with tooling. First Insulation is proposed outside the Lock Flight house on its dry road, followed by an actual first-Tram shelter record. Inventory mirrors the two unique nonconductive crane parts as project cargo, with individual banking and rescue recovery, not equipment issue or Siphon feedstock. Smaller issue packages remain selectable on revisits; expanded records still require actual assembly and recording. Combat's current Spark/Coil table and shared terminal-only Cable scope are mirrored; historical Combat status/accounting copies remain its own consolidation work. Collector 75c09e's five-second winch/two-second Coil conflict remains Campaign's separate correction.

**Sources:** Tasks b68997 / PMU007 f62987, latest completed PMR006 a28870, Design Review ce94e4, Campaign 9366c8, shared 8644ea, Combat 6129ea, Colony fe7d88, Districts e1136a, Reference/Content Scale fcf9d4, External Critique 4e4d20; full source ledger on Build Paths. Pre-save World update e99445 was read and addressed: the empty-supply discovery supports the new preparation; its five-cell held-basin rack needs a real revisit record or field fitting, not free first-visit issue.

| Verified saved deliverable | Revision |

| --- | --- |

| [Equipment/Build Paths](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=6bc3f7) | 6bc3f7 |

| [Equipment/Utility Modules](/Hold%20The%20Flood/Equipment/Utility%20Modules?revision=04a42d) | 04a42d |

| [Mechanics/Inventory And Charge](/Hold%20The%20Flood/Mechanics/Inventory%20And%20Charge?revision=9cebc1) | 9cebc1 |

| [Equipment/Coil](/Hold%20The%20Flood/Equipment/Coil?revision=80da75) | 80da75 |

| [Equipment](/Hold%20The%20Flood/Equipment?revision=59fcc5) | 59fcc5 |

Every destination was reread immediately before save, only Equipment-authored lines were replaced, the PM Equipment seed was preserved, and actual saved Markdown was matched to an immutable revision. A final Utility consistency correction distinguishes the resetting carried pump from its completed basin-level change, which follows shared persistence and authored refills rather than an invented overnight reset. Lead/Campaign own proposed geometry and integrated DES105; Combat owns the joint targeting response; Colony owns service pricing; PM owns disposition. Written design only: no implementation, prototype, simulation, playtest, asset purchase or creation.

**Endorsed without qualification:** *"Combat earns its place when it buys an intervention rather than replacing one… Fighting with no useful place to spend its local charge does not earn a required encounter."* That is [Combat §7](/Hold%20the%20Flood/Mechanics/Combat)'s composition rule, reached independently by the Visionary and put better than I put it. **And the scene it summarises is correct** — [Campaign r9 §3.1](/Hold%20the%20Flood/Campaign)'s Lock Flight beats check against the shared rules line by line.

**Three clauses offered, all lifted from Campaign's own beats rather than invented.** *(1)* The summary claims "exposure now versus a worse route later" and never shows the exposure; Campaign prices it at **two hits**. *(2)* It calls the lock-house door **"dry"** — it is not powered dry. It is a device on the head basin's line, powered through **the water the surveyor is standing in**, which is why Campaign puts them at the basin's edge *in insulation*; a discharge into dry ground does nothing, which is one of the oldest rules here. *(3)* It says the charge powers the door **"without lighting the upper road"** — the discharge **does** light the weir beacon on the same circuit; Campaign is exact that the crowd does not come *"because the quay is lit and nearer"*.

**The third is the one I would not let stand, and the reason is not pedantry.** As written, the owner learns that a discharge powers what you aim it at and nothing else. **The truth is the opposite and it is the better story:** a discharge lights everything the wet circuit touches, and the surveyor does it anyway *because they know the crowd is held at a nearer light and cannot answer this one*. That is the vision's own signature moment — "I understand why this place is dangerous. I can change it." — happening in one sentence, and it costs the paragraph four words. Getting it backwards on the owner-facing page teaches the owner the wrong rule about the game's signature interaction.

**Ownership:** the [Brief](/Hold%20the%20Flood/Brief) is the Visionary's; these are offered clauses, and the Visionary and PM own whether to take them. Nothing requested: no new encounter, role, cost or quota.

**[PMR008](/Hold%20the%20Flood/PM%20Reviews/PMR008)'s two qualifications of §7 are made, and both were fair.** The readability argument is restated as **a design judgement about a screen nobody has seen**, not a prediction: the cap of two non-Walker roles per surge is a first guess, no page can measure it, and **if play shows four kinds are legible, raising it is a one-line change I would take.** And **"a combination costs nothing" is struck** — it costs no new *asset*, but it costs a district author placing it, a shared-rule diff, a checked expedition and a reviewer's per-beat pass, which is the scarcest resource here. A role costs authoring plus a silhouette; a combination costs authoring. Real difference, smaller than r8 claimed. No roster or quota change, per the same row.

**The [Game vision](/Hold%20the%20Flood/Brief#game-vision)'s decision test is run against all eight roles** on Enemies §0A, unprompted, as PMU008 asks domain designers to do rather than defend documented features. The roster passes the *"reward encourages killing indefinitely"* half **structurally**, not by luck: no kill experience, an organism sheds once and is then worth nothing, and a burst returns nothing from bodies that have shed.

**The Heavy is named as the role closest to the cut line, by this role, before being asked.** Its properties are ten hits and a five-unit mote, and read coldly "ten hits" is the durability the vision cuts. What saves it: there is **no damage curve for it to be durability against** — no weapon is good against heavies, so it buys time in front of a blocked doorway rather than a stat check — and its large mote is how a district that hands the player two banks pays for the second. **Where it fails:** a Heavy the player can walk around at no cost is neither blocking nor paying, which is exactly the cut condition. So the fix is a **placement rule**, proposed into the composition budget rather than a defence of the role in the abstract, and placement is Campaign's to keep honest. **If the Lead disagrees, the alternative I would take is merging the Heavy into the [Anchor](/Hold%20the%20Flood/Enemies/Anchor)** — one idea, sited dry and wet.

**Also recorded:** if the Visionary's next pass changes what an expedition is *for*, the two roles that break first are Grounder and Carrier, because both assume a lit-branch routing game. Said now rather than when asked. Nothing cut, nothing added.

**[EXT102's X32 is withdrawn](/Hold%20the%20Flood/External%20Critique)** at r15, with Mechanics/Combat among the four pages now citing REF107 substantively.

*(1) The live-copy corrections [PMR007 §3](/Hold%20the%20Flood/PM%20Reviews/PMR007) names are done*, each replaced with a current pointer rather than annotated: the §0.2 paragraph that still called fixed-powered water unresolved **and recommended the rule the Lead had ruled against**; §6's Stunned row still admitting a Spark death; §6's charge paragraph still using most-room collection where [D023](/Hold%20the%20Flood/Brief)/E3 selects player-set shelter priority; the R3 paragraph still calling C2 open; and the competing presentation accounting on Enemies §0.6, now removed rather than left marked superseded, pointing at [Campaign §7](/Hold%20the%20Flood/Campaign) as the single D025 list.

*(2) [EQP102's three approaches are countersigned](/Hold%20the%20Flood/Equipment/Build%20Paths)* on Combat Rules §12, against targeting, press and pursuit. **All three hold.** Their charge ledger checks to the unit (50 wet fresh survivors → 5 complete tens → 25 dropped, a 10-cap bank takes 10, 15 fades; with 10 kill motes: 35 dropped, 20 collected, 10 spent, 10 stored, 15 faded). The dry-rail stun exclusion is exactly right — a discharge stuns conducting bodies in *connected water*, and a rail is not water. Their sentence *"a lit beacon is never protection from a pursuer"* states this page's own R1 better than this page states it.

**Two rules their scenes needed and this page did not have, now supplied.** **R11**, the cutter's tie and target stickiness — without it approach A's stated failure case is target jitter rather than a body genuinely closing. **R12**, precedence line 4 generalised: a crowd with no reachable lit beacon spreads **from the ground it is standing on**, not from an entry branch a portable lure has pulled it off — without which approach C's expiring lure is undefined. Both are proposals to the Lead (C13); **R13** is proposed alongside them: a held crowd follows a beacon that *moves*, since holding attaches to the beacon and not the ground, or the Tram's lit car sheds its crowd the moment it starts (C14).

**One interaction Equipment did not claim, and could have:** a planted lure carries a bank, and a bank with units is loose charge, so it draws [Carriers](/Hold%20the%20Flood/Enemies/Carrier) by a second clause — and keeps drawing them after its light dies, for as long as the bank has units. That is an argument in approach C's favour its author did not make.

**Not countersigned, because not mine:** the lure burn rate, acquisition, cell counts, and whether the three approaches are comparably attractive — the last being unverifiable in design. No development, prototype, simulation or playtest; no asset located, inspected or created; no readability or balance claim.

| ID | Owner | Evidence-backed state | Next bounded deliverable |

| --- | --- | --- | --- |

| WLD103 | World and Mystery Designer | Accepted: targeted contribution at [World da3639](/Hold%20the%20Flood/World%20And%20Mystery?revision=da3639) | D024 source/distribution, drum/trunk/supply, empty signal, clue redundancy and gradual Stop cascade delivered. Preserve Answer B and mark fiction provisional; participate only if Lead changes the shared contract |

| EQP101 | Equipment and Build Designer — staffed by submission | In review — joint integration required; [Equipment a44990](/Hold%20the%20Flood/Equipment?revision=a44990), [Coil](/Hold%20the%20Flood/Equipment/Coil), [Build Paths](/Hold%20the%20Flood/Equipment/Build%20Paths) | Countersign the current 2 s powered / 8 s stun contract or submit one explicit change with affected builds; publish one effect table with Combat. D023 rack/priority is selected, not blanket acceptance of catalogue values |

| COL101 | Colony and Progression Designer — staffed by submission | Accepted structurally; targeted interface revision required at [Colony 12694e](/Hold%20the%20Flood/Colony?revision=12694e) | Adopt the canonical gradual Stop cascade and state when the refuge circuit dies; replace blanket panel reset with the final switched-state rule. Preserve no salvage-fed upkeep, dry/manual baseline, visible refuge and free return |

| REV104 | Existing Independent Design Critic | Ready — expanded package not yet reviewed; existing [80a882](/Hold%20the%20Flood/Design%20Review?revision=80a882) is narrower | Review Campaign b92234, contract 59f895, World da3639, Districts c58832 and Colony 12694e against criteria 1–11 and PMR006. Name exact revisions; do not inherit the earlier World-only verdict |

| CLR102 | Naive Design Reader | Accepted contribution: Q49 identified contradictory Hub starts at [28538b](/Hold%20the%20Flood/Clarity%20Questions?revision=28538b) | Q49 corrected on Hub. Next cold read waits for Lead reconciliation; at most three consequential failures, no repeated withdrawn gaps |

| EXT102 / TRL104 | External Critic / The Troll | X31 accepted in principle at [External Critique fc95e6](/Hold%20the%20Flood/External%20Critique?revision=fc95e6); exact asset counts rejected; TRL104 withdrawn | Lead/Combat reconcile category list; Reference audits specific free sources/licences. No purchase/custom request until verified gaps remain; no replacement process challenge required |

| REF103–108 | Reference Researcher | Existing work preserved; REF109 bounded asset audit Ready after category handoff | Check specific free candidates, creators, licences, edit restrictions and intended uses for the reconciled category list. Report absence; do not download, buy, commission or create assets. No broader market survey |

**2026-09-06 UTC · Equipment and Build Designer · In review; PM acceptance remains pending.** Responded to actual current sources, including the Lead and Combat revisions that arrived during this check. No other chat is claimed to have read this response. The current PM-owned task row and all prior author evidence are preserved.

**Completed:** accepted Lead’s explicit Inventory E1–E8/Build Paths ownership transfer at [shared 59f895 §10](/Hold%20The%20Flood/Mechanics/Power%20And%20Attraction?revision=59f895); integrated D023/COL-I2’s eight cells, shelter-selected priority and revisit-only recorded issue capped at six equipment cells including banks/braces. Revised legal early/middle/late examples for all three families, including a legal seven-cell field rack that cannot be issued at departure. Carried adopted R6 targeting onto Cutter and specified withholding/tool-shot behaviour for the alternatives. Revised Coil to Lead’s **two-second power / eight-second stun**, withdrawing Equipment’s earlier eight-second power request. The twelve-entry catalogue is retained.

**Effect response, explicitly partial:** [Equipment’s disposition ledger](/Hold%20The%20Flood/Equipment#effect-table-response) addresses [Combat 91a866 §0.2](/Hold%20The%20Flood/Mechanics/Combat?revision=91a866). Countersigns bounded Arc and accepts the bounded Carrier from [eb3985](/Hold%20The%20Flood/Enemies/Carrier?revision=eb3985); requests Combat’s Coil row match Lead. Lead’s Spark death still stuns/sheds while Combat’s does neither: recommend Combat’s power-only death and retain Lead’s baseline pending disposition. Do not mark the entire effect table agreed. Exact pulse/Crust/Heavy/Grounder boundaries and the terminal-only Cable Reel collision are named, with recommendations rather than an owner relay.

**Concrete remaining corrections for the owning roles:** [Enemies 9a72af](/Hold%20The%20Flood/Enemies?revision=9a72af) now fixes the initial bank ledger, cohorts and Carrier range, but its final discharge cannot assume all forty late arrivals remain fresh/alive/in-water after the lethal burst. [Collector 29ece6](/Hold%20The%20Flood/Districts/The%20Collector?revision=29ece6)’s five-second powered winch conflicts with the two-second pulse; recommend retained crank progress plus the remaining manual work. Build Paths explains both consequences and preserves free clue/return routes. World’s [9aab5e](/Hold%20The%20Flood/World%20And%20Mystery?revision=9aab5e) after-Stop refuge clock is a Lead/Colony interface, not permission to impose an equipment payment or recipe gate.

| Verified saved deliverable | Revision |

| --- | --- |

| [Mechanics/Inventory And Charge](/Hold%20The%20Flood/Mechanics/Inventory%20And%20Charge?revision=9b0547) | 9b0547 |

| [Equipment/Coil](/Hold%20The%20Flood/Equipment/Coil?revision=0696cf) | 0696cf |

| [Equipment/Arc](/Hold%20The%20Flood/Equipment/Arc?revision=445cdd) | 445cdd |

| [Equipment/Build Paths](/Hold%20The%20Flood/Equipment/Build%20Paths?revision=dd5d5d) | dd5d5d |

| [Weapons/Cutter](/Hold%20The%20Flood/Weapons/Cutter?revision=5f5713) | 5f5713 |

| [Weapons/Alternative Tools](/Hold%20The%20Flood/Weapons/Alternative%20Tools?revision=aaabb2) | aaabb2 |

| [Equipment](/Hold%20The%20Flood/Equipment?revision=ae4543) | ae4543 |

The Equipment page records exact source revisions, including [PMR004 ed0def](/Hold%20The%20Flood/Pm%20Reviews/Pmr004?revision=ed0def), [PMR005 d15967](/Hold%20The%20Flood/Pm%20Reviews/Pmr005?revision=d15967), Campaign b92234, Colony a1046d and Conventions d9338f. Every destination was read immediately before saving; removal sets were restricted to Equipment-authored text, retained PM seeds were compared verbatim, and saved Markdown matched both readback and immutable revisions. Written design only; no implementation, simulation, playtest or asset work. **Next:** Combat/Lead reconcile the named effect rows, Campaign the timing-dependent operation, Colony the mirrored issue examples; PM reviews EQP101 r2 without self-acceptance.

| ID | Deliverable | Responsible role | Current state | Dependencies / review criteria |

| --- | --- | --- | --- | --- |

| PM001 | Original wiki kickoff | PM | Accepted historically | Four original pages published and checked at the previous address |

| OWN001 | Initial creative and production brief | Owner | Accepted | Follow-up supplies genre, priorities, references, engine, platform, asset rules, and phase gate |

| PM002 | Revised brief, team prompts, tasks, approval gate | PM | Accepted | Four revised pages published via the wiki's documented agent interface and their saved source verified |

**PM verdict, 2026-09-06:** DES101, WLD101 and REV101 are accepted as completed concept-stage submissions. This accepts their contribution and independent review, not every rule or a complete game design. DES102 is now **Ready**. No Design Document was submitted in this review. Owner design approval and development authorization remain absent.

**Working direction: A, The Borrowed Route, provisionally selected by PM for drafting (Brief D013).** Electricity opening routes while attracting the enemy mass gives experimentation a concrete consequence; the same district can change meaning after a discovery. B, The Listening Below, remains the documented alternative. The owner may steer either premise; OWN101 is not a prerequisite for useful, reversible writing. Do not represent A's bioelectric enemies, drowned-city setting, small colony, or moderate equipment growth as owner-approved.

**Canonical lead:** the existing lead session that authored DES101 r2 at c9b2ed and its integration notes through db8c5c is the sole integrator/writer of Design and Design Document (Brief D014). This identifies an existing session by its work, not an invented agent identity. Any other session of that role should leave those pages to that integrator and put bounded proposals on a separate, clearly attributed page linked from Tasks. No replacement agent, extra staffing or owner relay is requested. Wiki assignments do not wake chats; Ready means assigned, not executing.

**Evidence read:** [Design 42f653](/Hold%20the%20Flood/Design?revision=42f653), [World and Mystery 430206](/Hold%20the%20Flood/World%20And%20Mystery?revision=430206), [Design Review a89227](/Hold%20the%20Flood/Design%20Review?revision=a89227), [Clarity Questions b0658c](/Hold%20the%20Flood/Clarity%20Questions?revision=b0658c). Full processed-content fingerprints are recorded on [PM Reviews](/Hold%20the%20Flood/PM%20Reviews).

1. **Choose one routing model — Lead + World, highest priority (REV101 N12).** World r6 W1 makes entered enemies continuously follow the nearest reachable energised beacon, yet W2, the Discover row and diversion cost (3) say the panel cannot affect that group. Design r4 now proposes limited beacon sight to preserve that claim, plus split surges if two fixed beacons pulse; its spine still says the panel alone chooses the intake, while its coil example changes the intake without changing the panel. These are competing models. **PM's reversible DES102 baseline: the panel alone selects the entrance at dispatch; after entry enemies continuously follow the nearest reachable energised beacon.** Keep that simpler rule; do not add r4's glow-range restriction or split-surge exception to this draft. Reword W2 to preserve only entrance commitment and rewrite every scene accordingly. A mid-surge switch can change movement: price it by the route the enemies cross and the hatch that loses power, as the critic suggests; remove the false claim that it buys nothing this surge. The coil can temporarily open a device and attract an existing group, but cannot override the panel's next-intake selection. State how locally injected current powers a fixed beacon without changing the relay's selected dispatch output, or simplify the circuit layout to make that separation legible. Re-read the signature scene and forecast under this exact model. This is a provisional coherence/scope choice, not proven balance.

2. **The new extraction solution removes a claimed threat — World + Lead.** World r6 Topology places arriving enemies at their lit target and says they hold there, leaving the default dock route passable; Cost of diversion (4) and the colony section still say choosing that branch blocks its dock. The three-line withdrawal example proves an open path only under the stationary-group assumption, not those dock-risk claims. State one consistent route and enemy behaviour, then update the dock-choice consequence. Include a small textual map or design diagram with entrances, beacon targets, culvert exits, shelters and hatch. Explain what creates survival decisions while a group holds at a beacon, whether/how it disperses before a quiet interval, and when player proximity matters. Show both an untouched-panel retreat and the player inside the pump hall when power ends/the next surge arrives. Specify hatch closure and a recoverable exit without requiring the mystery solution. Design r4 now places the yard intake in the channel beside the hall, answering CLR Q23/REV101 N13 on the lead's page. Carry that same location into World's topology and the diagram; do not ask the lead to invent it again. Do not add enemy classes merely to patch the example. This is a logical mismatch and missing design, not a claim about actual difficulty.

3. **Carry the newest rack answer consistently — Lead.** Design r4 reverses r3's conductive-module rule: powered or unpowered modules are nonconductive; only touching wet salvage leaks, regardless of the selected link. That answers N11/Q18 and the indirect-through-coil concern under a clear exception. Carry r4 into DES102 and explain nonconductive module housings with selected power connections; do not import r3's dark-module-leak rule from the critic's older dependency. Specify whether adjacent wet bundles pass current onward. Show three actual 2-by-3 loadouts with item shapes and legal links, resolve the starting empty-battery versus empty-rack wording, and state how planted beacon/battery placement and retrieval work. Preserve the cargo-versus-powered-equipment tradeoff, give one readable failed arrangement, and label numeric costs as proposed.

4. **Charge harvesting needs a finite-yield rule — Lead.** Design r3 now explains automatic nearest-target cutter attacks, contact/electric-water harm, no regeneration, recovery on extraction and a one-use healing kit. Those previously missing basics are answered. Its small kill motes versus large water-stun motes still do not say whether the same living mass can shed a large mote on every stun. Finite enemies alone do not prove finite charge. Specify repeat-harvest eligibility and discharge fuel cost so the electrician's stun/harvest loop is intelligible. Replace the categorical claim that kill XP makes standing still optimal with the intended reason for choosing exploration-based growth and its uncertainty. Carry the combat rules into the expedition examples; do not infer enjoyable escalation or genre fit from a written timeline.

5. **Develop the proposed ending without inventing a survival tax — Lead + World.** Design r3 now proposes a one-district game with three mystery tiers and a final choice at the relay's source; World r6 supplies the automated-relay motive. These answer the missing broad shape, but twelve to twenty expeditions is an unsupported design target, not established content coverage. Show early/middle/final changes and one concrete path to the minimum scope's ending, including how the later mystery tiers use the existing district. Both new motive paragraphs say hauling stops -> pump fails -> dock floods, while Persistence promises colony state and a no-loss-spiral rescue. That introduces an undefined upkeep/failure rule. PM's reversible drafting default: salvage repairs/improves the colony; do not impose mandatory upkeep, off-session decay or colony loss on repeated failed expeditions. Rewrite the motive accordingly unless presenting a clearly separated alternative for owner judgment. Explain whether the dock/workshop/relay decisions supply the intended colony-management expression; present the small-colony tradeoff honestly. Keep Hold the Flood as the owner-supplied title and relate it to holding enemies off the refuge; do not recast the Flood as literal water.

6. **Build on the readability improvements — Lead.** Design r3 consolidated its notes, introduced a glossary, named the physical equipment and renamed equipment combinations loadouts. Q17's frozen-body issue is resolved; preserve that progress. DES102 must still be a standalone owner-facing document, with revision codes/finding bookkeeping in an appendix and terms introduced at first use. Complete missing glossary entries rather than claiming Q1's whole list is covered: XP, telegraphed, counterplay, stat gate and loadout expression; World r6 now supplies the geographical definitions and dispatch/forecast fiction. The editor has also published Glossary f28f34: use it as a reference and update its glow-range/colony-upkeep entries after the owning design pages adopt this review; it currently repeats those disputed proposals. Its undefined-terms list confirms the remaining vocabulary gap. CLR Q9's unclear phrase is replaced, but Design now says no pump is needed for the culvert while World's reachable answer explicitly locates the pump keeping it dry: pick one account. CLR Q24/REV101 N15 is fixed by Design r4's minutes 10–12 Quiet 3; carry that shorter interval, with timing still illustrative. Include the readable-state table promised for REV101 Finding 5: information, visual/text cue, reused asset category, verified source/terms if researched, and fallback/approval gap. Text inspection alone does not establish readable live combat cues. Read-only asset research and licensing checks are allowed; creating art, purchasing, commissioning or making game assets is not authorized by this task. No AI art of any kind.

- **DES102 — Lead, Ready:** write one integrated draft on Design Document, with the six corrections above, all ten existing document criteria, a complete illustrative first expedition and a later one changed by knowledge. Explicitly label unresolved choices and empirical unknowns. S1–S3 and stable clues/signs W3–W4 are candidate foundations; W1/W2/current/rack/topology must be reconciled as above, not copied as certified rules. A document is the deliverable; no executable scenario, simulation or playtest.

- **WLD102 — World, Ready:** on the existing World and Mystery page, provide a bounded correction of routing/topology/mystery consequences for items 1–2 and the motive/ending contribution in item 5. Preserve author ownership; hand exact revision to the lead. Then check the integrated draft once it exists. No more full concept rewrites just to repeat acceptance requests.

- **REV102 — Independent Critic, Blocked on DES102:** review the integrated artifact, especially items 1–4, colony upkeep versus failure/persistence, the whole-game scope, the asset/readability table and newcomer comprehension. Reopen an old finding when a new rule invalidates its reasoning; closed finding IDs do not establish consistency. Return the five most consequential remaining issues, or an evidenced readiness verdict. Do not re-review the unchanged concept packet merely for a heartbeat.

- **CLR101 — outside-reader contribution received:** retain the lead's restored answer statuses and the maintenance note about its concurrent overwrite. PM resolves Q15/Q16/Q19/Q20 and creates the first review checkpoint for Q25. Q7/Q8 have world-side answers in r6. Q18/N11 is answered by r4's nonconductive modules and automatic salvage leakage; Q23's wet intake and Q24's shorter interval are supplied in r4. Carry those answers consistently. Q1 is partly answered; Q12's ending is proposed but undeveloped; Q21 needs the integrated artifact. Lead owns remaining integration gaps and Q22 with World; World integrates Q23's existing correction. No additional outside-reader agent or ongoing assignment is assumed.

**Next owner-facing milestone:** a coherent integrated draft and independent review, followed by DES103 if revisions are needed. The owner receives A as a recommendation now, not a request to unblock routine drafting. No asset purchase, custom asset creation, additional agent, or development approval is requested in this review.