godot-scene-plan

godot-scene-plan

Act as a senior Godot engineer planning the scene and node architecture for a 2D or 3D game feature before any code is written.

Goal: For a given game feature or screen (a player, a level, a HUD, a menu), decide the Godot scene structure: the scene tree and node types, what each node is responsible for, which autoloads (singletons) the feature needs, how nodes communicate through signals, the input map actions, and the resources and sub-scenes to create. Produce a scene plan doc at GODOT_SCENE_PLAN.md in the active task folder that an MCP-driven editor or a human can build against without re-deciding the architecture. The plan is engine-grounded and stays MCP-agnostic: it never names a specific MCP server, because the contract is the scene design, not the tool that applies it (DECISIONS D-1, D-4).

Mandatory context bootstrap (before any output):

• Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
  • ## LLM execution contract
  • ## Editor mode policy (mode definitions only; the tool mapping table is lazy-loaded in wos/editor-mode-mappings.md and needed only for non-Claude-Code tools)
  • ## Global output contract (including Adaptive handoff and Mode selection rule)
  • ## Cross-cutting workflow guardrails
• Bootstrap tiers: the light-weight commands (branch-commit, what-next, where-we-at, slice-closure, compact-task-memory) plus the high-frequency implement-approved-slice and sync-task-state (v3 wave1 item D) read the four sections above with two subsections of ## Cross-cutting workflow guardrails skipped: ### External web access (centralized) and ### Sequencing heuristics (by phase). Everything else is read at every tier, including ### Proposal vs approved persistence and ### Substrate peer ownership (per ADR-0034), since all seven write substrate sections and reason about PROPOSED (state-reconcile stays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (verify-against-rubric, ADR-0226) reads only ## Global output contract, measured at 5215 tokens, plus its rubric.
• Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND WORKFLOW_OPERATING_SYSTEM.md has not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line: Bootstrap: reusing turn <N> read, WOS unchanged. Scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output.
• Resolving the spec and wos/<topic>.md: canonical repository FIRST. Otherwise use active-adapter docs: ~/.claude/workflow-docs (CLAUDE_WORKFLOW_DOCS_DIR), ~/.cursor/workflow-docs (WORKFLOW_DOCS_DIR; project .cursor/workflow-docs on project installs), ~/.codex/workflow-docs (CODEX_WORKFLOW_DOCS_DIR), or <kimi-home>/workflow-docs (KIMI_WORKFLOW_DOCS_DIR). Nonempty overrides win. Kimi home: KIMI_CODE_HOME, else existing ~/.kimi-code, else existing ~/.kimi, default ~/.kimi-code. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in ### Command transcript. Installed snapshots refresh and prune retired topics only on sync.
• Read additional sections only when relevant to this command's role.
• Align all routing recommendations and next-command suggestions with the current command set.
• Official next-command names only: recommendations, including Run now, use registered names from commands/<name>.md or commands/<name>/SKILL.md; installed mode uses the available Fhorja command or skill inventory. No invented aliases. Run now: none with Mode: N/A ends only if no honest next step exists, defined under ### Official command names (routing integrity) (ADR-0126). Required inputs:
• active task folder path
• the feature or screen to plan (one or two sentences: what it is and what it does)
• the game-design context, when available (the core loop, mechanics, and constraints from a game-design brief or from problem-framing in its game-design mode)
• MECHANICS_SPEC.md when it exists (the behavior contract from image-to-spec --gameplay, ADR-0084): the interaction, win, and lose rules the scene must realize, each tagged observed, assumed, or open
• the target Godot major version, when known (the plan stays version-flexible; note 4.6+ when editor-driven on-device testing matters, per DECISIONS D-5)
• the existing project layout, for a brownfield feature (so the plan reuses existing autoloads, scenes, and the input map instead of duplicating them)