9Router (9router-app) — a local AI routing gateway + Next.js dashboard. It exposes one OpenAI-compatible endpoint (/v1/*) and routes traffic across 40+ upstream providers with format translation, model-combo fallback, multi-account fallback, OAuth/API-key credential management, token refresh, quota/usage tracking, and optional cloud sync. Two published artifacts live in this one repo: - The dashboard + gateway (root package.json, 9router-app) — the Next.js server that does the actual routing. - The CLI launcher (cli/, published to npm as 9router) — a separate…
Use the TYPE: Description format: Common types: ENH (feature/enhancement), BUG (fix), TST (test), DOC (docs), CHORE (maintenance/refactor), BLD (build system changes). Scope is optional but encouraged — use the component name (e.g. rust-client, gc, dashboard-api). - Subject line: ≤ 50 characters. Keeps it readable in git log --oneline, GitHub PR lists, and rebase tooling. - Blank line between subject and body (required — many tools use this to split them). - Body lines: wrap at 72 characters. Leaves room for…
This file provides guidance for working with the Repomix browser extension. Cross-browser extension (Chrome/Firefox/Edge) that adds Repomix integration to GitHub repository pages. Uses Manifest V3 with content scripts to inject a "Repomix" button directly into GitHub's UI.
This file provides guidance to Claude Code when working with this repository. Claude HUD is a Claude Code plugin that displays a real-time multi-line statusline. It shows context health, tool activity, agent status, and todo progress. Key insight: The statusline is invoked by Claude Code after each interaction (new assistant message, /compact finishing, permission-mode changes, vim-mode toggles), debounced at 300ms — not on a fixed polling loop. Each invocation: 1. Receives JSON via stdin (model, context, tokens - native accurate…
This file is intentionally short. Do not copy workflow, build, storage, or UI rules here; those details drift quickly when repeated across agent entrypoints. - Run bd prime before doing tracked work. - Follow go.mod and AGENTINSTRUCTIONS.md for build and test commands; do not hard-code toolchain versions here. - Beads uses Dolt as the issue database. Use bd dolt push / bd dolt pull for issue data sync; do not use export/import as a routine git workflow. - The CLI…
beads (command: bd) is a Dolt-powered issue tracker for AI-supervised coding workflows. Git integration is optional — see BEADS_DIR + --stealth for git-free operation. We dogfood our own tool. IMPORTANT: See AGENTS.md for complete workflow instructions, bd commands, and development guidelines. Beads uses Dolt as its storage backend — a version-controlled SQL database: Core implementation: - Dolt storage: internal/storage/dolt/ - Embedded runtime: internal/storage/embeddeddolt/ - Server runtime: internal/doltserver/, internal/storage/db/, and internal/storage/doltserver/ - Sync commands: cmd/bd/dolt*.go, cmd/bd/sync*.go See internal/types/types.go: - Issue: Core…
Keep repo-wide decisions here; procedures belong in CONTRIBUTING.md, area instructions and task skills. Read the matching skill before changing an area, then only the references needed. - Before committing, setup…
Guidance for AI agents (Claude Code, Cowork, and others) working in this repository. This file is the single source of truth for how the project is structured and maintained. PM Skills (phuryn/pm-skills) — a marketplace of 9 independent plugins (68 skills, 42 commands) that bring structured product-management workflows to AI coding assistants. Built for Claude Code and Claude Cowork; the skills are also compatible with other agents (Gemini CLI, Cursor, Codex CLI). Owner: Paweł Huryn — pawel@productcompass.pm — https://www.productcompass.pm
Claude Code marketplace plugin providing AI-powered content generation skills. Version: 2.0.0. Skills are exposed through the single baoyu-skills plugin in .claude-plugin/marketplace.json (which defines plugin metadata, version, and skill paths). The repo docs still group them into three logical areas: Each skill contains SKILL.md (YAML front matter + docs), optional scripts/, references/, prompts/. Top-level scripts/ contains repo maintenance utilities (sync, hooks, publish). TypeScript via Bun (no build step). Detect runtime once per session: Execute: ${BUN_X} skills/<skill>/scripts/main.ts [options] Priority: project skills/ →…
This folder is the quality assurance layer for the Claude Code Game Studios skill/agent framework. It is self-contained and separate from any game project. The spec: field in catalog.yaml is the authoritative path for each skill/agent spec. Always read it rather than guessing the path.
Indie game development managed through 49 coordinated Claude Code subagents. Each agent owns a specific domain, enforcing separation of concerns and quality. Note: Engine-specialist agents exist for Godot, Unity, and Unreal with dedicated sub-specialists. Use the set matching your engine. @.claude/docs/directory-structure.md 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.…
When authoring or editing files in this directory, follow these standards. The 8 GDD sections, in order: 1. Overview — one-paragraph summary 2. Player Fantasy — intended feeling and experience 3. Detailed Rules — unambiguous mechanics 4. Formulas — all math defined with variables 5. Edge Cases — unusual situations handled 6. Dependencies — other systems listed 7. Tuning Knobs — configurable values identified 8. Acceptance Criteria — testable success conditions How many are REQUIRED depends on modes.workflow — all…
When authoring or editing files in this directory, follow these standards. Use the ADR template: .claude/docs/templates/architecture-decision-record.md Required sections: Title, Status, Context, Decision, Consequences, ADR Dependencies, Engine Compatibility, GDD Requirements Addressed Status lifecycle: Proposed → Accepted → Superseded - Never skip Accepted — stories referencing a Proposed ADR are auto-blocked - Use /architecture-decision to create ADRs through the guided flow TR Registry: docs/architecture/tr-registry.yaml - Stable requirement IDs (e.g. TR-MOV-001) that link GDD requirements to stories - Never renumber existing IDs —…
When writing or editing game code in this directory, follow these standards. The LLM's training data predates the pinned engine version. Always check docs/engine-reference/ before using any engine API. Do not guess at post-cutoff API signatures — look them up first. - All public APIs require doc comments - Gameplay values must be data-driven (external config files), never hardcoded - Prefer dependency injection over singletons for testability - Architecture decisions go in docs/architecture/ as ADRs — how many depends on…
Guidance for working inside agent-launcher/. See the root CLAUDE.md for repo-wide rules. A plugin that scaffolds and launches Claude Managed Agents (CMA) in the user's own Anthropic account, organized around a per-session goal that compiles into a loop or workflow. Inspired by anthropics/launch-your-agent (Apache-2.0); independent re-implementation, not a fork. 1. Deterministic scaffolders only. Every script under skills//scripts/ is stdlib-only and makes *no* network/API calls. Live launches are emitted as BYOK curl. Do not add requests, anthropic, or any network client.…
This guide provides comprehensive instructions for creating *cs- prefixed agents** that seamlessly integrate with the 346 production skills in this repository (count derived via scripts/derive_counters.py). *cs- agents** are specialized Claude Code agents that orchestrate the repository's 346 skills. Each agent: - References skills via relative paths (../marketing-skill/) - Executes Python automation tools from skill packages - Follows established workflows and templates - Maintains skill portability and independence Key Principle: Agents ORCHESTRATE skills, they don't replace them. Skills remain self-contained and…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
decoluaCLAUDE.md
