Borrowing it
Nothing to install: this file belongs to kamwoh/yume. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kamwoh/yume/master/CLAUDE.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kamwoh/yume/claude-md)<a href="https://agentmods.dev/instructions/kamwoh/yume/claude-md"><img src="https://agentmods.dev/badge/instructions/kamwoh/yume/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05517 | $0.05517 |
| Opus 5 | $0.02759 | $0.02759 |
| Sonnet 5 | $0.01103 | $0.01103 |
| Haiku 4.5 | $0.00552 | $0.00552 |
Grade A, and why
yume CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yume (夢) — JSON-driven game framework on Godot
You are working on Yume: a JSON-declarative content layer over Godot 4.6.1 that lets non-programmers (and LLMs) generate working games without writing GDScript per-game. Per ADR 0021, the engine ships a fixed verb set (the "seven primitives" + a small interpreter); each game's mechanics are pure JSON.
Quick Start
This repo ships the framework (engine, skills, scaffolding scenes,
shared engine libraries) but NOT specific game demos. Demos live at
godot/data/demo_<name>/ and are gitignored — generate locally via the
pipeline below or copy from another working tree.
To generate a new game from a prose pitch:
/yume-design "a roguelike where vampires steal HP from light sources" --autonomous
The /yume-design skill orchestrates text → GDD → world plan → level
design → rules → JSON → assets → QA. Output lands at
godot/data/demo_<slug>/.
To run a locally-generated demo:
./scripts/play.sh <name> # falls back to scenes/play.tscn --game=<name>
./scripts/play.sh <name> --capture # auto-capture for visual QA
Framework structure
yume/
├── .claude/ ← Skills + rules + settings
│ ├── skills/yume-*/SKILL.md (38 specialist skills, Tier 2.6)
│ └── rules/ (path-scoped invariants)
├── godot/ ← Godot project (engine + scaffolding; demos gitignored)
│ ├── data/ ← shared engine libraries (TRACKED)
│ │ ├── shapes.json (code-draw shape library)
│ │ ├── meshes.json (3D mesh library)
│ │ └── sounds.json (procedural SFX library)
│ ├── data/demo_<name>/ (per-game content — NOT TRACKED, gitignored)
│ │ ├── entities/ (definitions + initial instances)
│ │ ├── world/rules.json (world physics rules — ADR 0009)
│ │ ├── game/goals.json (game logic — win/score/transition)
│ │ ├── game/flow.json (multi-level progression — ADR 0006)
│ │ ├── levels/<n>/ (per-level entities + rules)
│ │ ├── world/state.json (initial _engine entity state — ADR 0047)
│ │ ├── world/zones.json (zone-state primitive — ADR 0031, optional)
│ │ ├── audio/cues.json (semantic-event → SFX mapping)
│ │ ├── ui/strings.json (localizable text)
│ │ ├── scene.json (camera + lighting + ground + tick_seconds)
│ │ ├── screens.json (title/pause/etc. — ADR 0011, optional)
│ │ ├── save_policy.json (what persists — ADR 0010, optional)
│ │ ├── settings_schema.json (settings — ADR 0013, optional)
│ │ └── tutorial.json (overlay sequencing — ADR 0012, optional)
│ ├── scripts/engine/ (engine: rule, query, effect, scheduler, etc.)
│ ├── scenes/ (TRACKED scaffolding only)
│ │ ├── play.tscn (universal launcher — `--game=<name>`)
│ │ ├── test_main.tscn (engine unit tests)
│ │ └── scenario_test.tscn (per-game scenario test runner)
│ └── project.godot
├── docs/ ← Documentation (active)
│ ├── 30_framework_primitives.md (the contract — invariant-bearing)
│ ├── 31_text_to_game_pipeline.md (Tier 2.5 strategic plan)
│ ├── 32_mda_for_yume.md (Mechanics → Dynamics → Aesthetics)
│ ├── adr/NNNN-*.md (architecture decisions)
│ ├── engine-reference/ (api manifest, Godot pinning)
│ ├── games/<name>/ (per-game GDDs, plans, reviews)
│ └── timeline/ (decision diary)
├── scripts/play.sh ← Run a demo (sync + launch)
├── tools/gen_api_manifest.py ← Regenerate engine API manifest
├── task_plan.md ← Index → .claude/plan/{backlog,archive}.md
└── CLAUDE.md (this file)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 410 lines · 5,517 tokens per session scan A f638832c484e
yume CLAUDE.md is an instructions file published in the GitHub repository kamwoh/yume (21 stars, last pushed 2mo ago), licensed MIT. It adds 5,517 tokens to every session, about $0.0276 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.