Files
Claude-Code-Game-Studios/CLAUDE.md
T
DonchitosandClaude Opus 5.5 be8993bbc5 Release 1.1.3 — long skills keep their later steps
Fix release for 1.1.2: the 14 longest skills keep their later phases
after a compaction, a question nobody answered is never taken as an
answer, settings read the same from a subfolder, the commit check works
for a project in a subfolder of a larger repository, every skill opens
with a title, and the shipped allow rules no longer approve deleting a
branch or writing files without asking. Details in CHANGELOG.md; upgrade
steps in UPGRADING.md (v1.1.2 → v1.1.3).

Refs #83
Refs #133

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko
2026-10-08 17:52:48 +11:00

84 lines
3.5 KiB
Markdown

# Claude Code Game Studios -- Game Studio Agent Architecture
Indie game development managed through 49 coordinated Claude Code subagents.
Each agent owns a specific domain, enforcing separation of concerns and quality.
## Technology Stack
- **Engine**: [CHOOSE: Godot 4 / Unity / Unreal Engine 5]
- **Language**: [CHOOSE: GDScript / C# / C++ / Blueprint]
- **Version Control**: Git with trunk-based development
- **Build System**: [SPECIFY after choosing engine]
- **Asset Pipeline**: [SPECIFY after choosing engine]
> **Note**: Engine-specialist agents exist for Godot, Unity, and Unreal with
> dedicated sub-specialists. Use the set matching your engine.
## Project Structure
@.claude/docs/directory-structure.md
## Engine Version Reference
<!-- ENGINE-REFERENCE-IMPORT: the line below is engine-specific. /setup-engine
rewrites it to @docs/engine-reference/<engine>/VERSION.md for the chosen
engine, so a Unity or Unreal project stops loading the Godot reference every
session. It defaults to Godot (the template's example engine); skills that
need the pinned version read docs/engine-reference/<engine>/VERSION.md on
demand regardless of this import. -->
@docs/engine-reference/godot/VERSION.md
## Technical Preferences
`project.yaml` at the repo root is the primary config store — engine, specialists,
naming, platform, performance, modes. Skills resolve it via `resolve_config`
(see `.claude/docs/config-resolution.md`).
`.claude/docs/technical-preferences.md` is the **legacy fallback**, read on demand
when a key is absent from `project.yaml`. It is no longer imported here: before
`/setup-engine` runs it is almost entirely `[TO BE CONFIGURED]` placeholders, and
after it runs `project.yaml` holds the real values.
## Coordination Rules
@.claude/docs/coordination-rules.md
## Collaboration Protocol
**User-driven collaboration, not autonomous execution.**
Every task follows: **Question -> Options -> Decision -> Draft -> Approval**
- Agents MUST ask "May I write this to [filepath]?" before using Write/Edit tools
(exempt: `active.md` appends, agent memory, a subagent's new file at the path
its orchestrating skill named; see `.claude/rules/agent-memory.md`)
- Agents MUST show drafts or summaries before requesting approval
- Multi-file changes require explicit approval for the full changeset
- No commits without user instruction
- A skipped or dismissed question is not an answer: act on nothing, re-ask in
plain text and wait
- Started outside this file's folder? Warn first: hooks, deny rules and the
ask-first mode load only when Claude Code starts here
See `docs/COLLABORATIVE-DESIGN-PRINCIPLE.md` for full protocol and examples.
> **First session?** If the project has no engine configured and no game concept,
> run `/start` to begin the guided onboarding flow.
## Coding Standards
@.claude/docs/coding-standards.md
## Context Management
Read `.claude/docs/context-management.md` on demand — it is a reference, not
session context. Two of its conventions are load-bearing and cited by name
elsewhere in the repo, so they are restated here rather than lost:
- **`production/session-state/active.md` is the session checkpoint.** The file is
the memory, not the conversation. Read it first after any compaction, crash, or
`/clear`.
- **Helpers in `.claude/scripts/` emit observations, never verdicts.** A script
that scores or judges will eventually contradict a mode or override it cannot
see. (Cited by `artifact-check.sh` and `adr-dep-graph.sh`.)