docs(spec): errand_runner redesign — donut goal, forced-path maps, 3 memory types, results screen

docs(scenario): errand_runner design spec (visual-only city errand + find-your-body discovery)

docs(scenario): take_a_seat design spec (central table + far-slot persona)

docs: implementation plan for multi-agent memory + predator visuals (+ spec resource_race turn-order fix)

docs: simplify predator-first turn order (swap inside step, no loop changes)

docs: spec for multi-agent memory scenarios + predator/agent visual & turn-order refresh

docs(spec): preserve agent/provider/registry candidates from untracked game/

docs(spec): preserve arena/leaderboard/db design from untracked interface/

docs(spec): proteus game/web restructure design

docs: spec for food resources + scripted memory policies + LLM-spectate fix

docs: spec for memory-movement replay + pack_evade wall terrain

docs(spec): pack_evade scenario (64x64, multi-cell, manual memory) + web LLM spectating designs

docs(cp7): design spec — LLM-generated memory pre-roll (hybrid handover)

docs(web): interactive color-grid web play — brainstormed design (SSOT)

docs(cp6): design — difficulty layouts + category-specific eval + human-baseline compare

docs(cp5): brainstormed design — HumanAgent + trace viz (engine-replay reconstruction)

docs: PROTEUS arena end-to-end slice design spec