mirror of
https://github.com/Donchitos/Claude-Code-Game-Studios.git
synced 2026-10-16 01:37:05 +00:00
`project.yaml` at the repo root is now the single source of truth for a project's configuration, replacing `production/stage.txt`, `production/review-mode.txt` and `.claude/docs/technical-preferences.md` (all three still read as a fallback; nothing is force-deleted). **`modes.rigor` — one question instead of six.** `minimal`, `standard` or `full` fronts six knobs: `modes.workflow`, `docs.density`, `qa.level`, `modes.story_granularity`, `modes.review_mode` and `team.size`. It defaults to `minimal`, which is a change from 1.0's behaviour: the heavier tier was measured costing several times more to reach working code without producing a better result, and returning nothing when a fresh developer inherited the project. Pin `modes.rigor: standard` to keep 1.0's process level. Also in this release: - `/settings` to view or change any setting, and `project.local.yaml` for per-developer preferences that should not be committed. - `system_overrides` to hold one system to a higher standard than the rest of the project, and `testing.strict` to set per test type whether missing evidence blocks a story or warns. - A story that changes anything the player sees is not closed until the game has been launched, observed, and a screenshot retained in `production/qa/evidence/`. A parse check is not a run. This holds at every rigor level, including `minimal`, where automated tests are waived but the look is not. - The code root is engine-specific and enforced as such: Godot `src/`, Unity `Assets/`, Unreal `Source/<Module>/`. Two of the three will not build a project laid out any other way. - Migration tooling for existing projects: `.claude/scripts/migrate-v1-config.sh` converts a 1.0 layout, non-destructively by default, with a report to review before `--finalize` deletes anything. - Ask-before-write holds regardless of personal automation settings. Upgrading from 1.0 or earlier: see UPGRADING.md. Full list of changes: CHANGELOG.md. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016xvzG3i7pWQg4LjyDwWMXd
Engine Reference Documentation
This directory contains curated, version-pinned documentation snapshots for the game engine(s) used in this project. These files exist because LLM knowledge has a cutoff date and game engines update frequently.
Why This Exists
Claude's training data has a knowledge cutoff (currently May 2025). Game engines like Godot, Unity, and Unreal ship updates that introduce breaking API changes, new features, and deprecated patterns. Without these reference files, agents will suggest outdated code.
Structure
Each engine gets its own directory:
<engine>/
├── VERSION.md # Pinned version, verification date, knowledge gap window
├── breaking-changes.md # API changes between versions, organized by risk level
├── deprecated-apis.md # "Don't use X → Use Y" lookup tables
├── current-best-practices.md # New practices not in model training data
└── modules/ # Per-subsystem quick references (~150 lines max each)
├── rendering.md
├── physics.md
└── ...
How Agents Use These Files
Engine-specialist agents are instructed to:
- Read
VERSION.mdto confirm the current engine version - Check
deprecated-apis.mdbefore suggesting any engine API - Consult
breaking-changes.mdfor version-specific concerns - Read relevant
modules/*.mdfor subsystem-specific work
Maintenance
When to Update
- After upgrading the engine version
- When the LLM model is updated (new knowledge cutoff)
- After running
/refresh-docs(if available) - When you discover an API the model gets wrong
How to Update
- Update
VERSION.mdwith the new engine version and date - Add new entries to
breaking-changes.mdfor the version transition - Move newly deprecated APIs into
deprecated-apis.md - Update
current-best-practices.mdwith new patterns - Update relevant
modules/*.mdwith API changes - Set "Last verified" dates on all modified files
Quality Rules
- Every file must have a "Last verified: YYYY-MM-DD" date
- Keep module files under 150 lines (context budget)
- Include code examples showing correct/incorrect patterns
- Link to official documentation URLs for verification
- Only document things that differ from the model's training data