Borrowing it
Nothing to install: this file belongs to ryancampbell/kart-royale. 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/ryancampbell/kart-royale/main/CLAUDE.mdgit clone --depth 1 https://github.com/ryancampbell/kart-royaleWrote 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/ryancampbell/kart-royale/claude-md)<a href="https://agentmods.dev/instructions/ryancampbell/kart-royale/claude-md"><img src="https://agentmods.dev/badge/instructions/ryancampbell/kart-royale/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ryancampbell/kart-royale/claude-md"><img src="https://agentmods.dev/badge/instructions/ryancampbell/kart-royale/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02881 | $0.02881 |
| Opus 5 | $0.01440 | $0.01440 |
| Sonnet 5 | $0.00576 | $0.00576 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
kart-royale 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 9d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo
A kart racer in Three.js with zero art assets — every texture, mesh, material and sound is generated in code at load time. Written almost entirely by Claude agents working in parallel. This file is the handover note: the contract to code against, the traps that have already cost real rounds, and how to tell whether a change actually helped.
Read README.md for what the project is, and ART_DIRECTION.md for what it is
supposed to look like — §9 of that file is the scoring rubric, and it is the bar.
Commands
npm run dev # vite dev server
npm run build # tsc --noEmit && vite build — this is the gate, it must pass
npm run preview # serve the production build
Never start a bare npx vite for a test harness. Use tools/vite-server.mjs,
which spawns the binary directly, kills the whole process group on teardown, and
refuses to adopt a server that is already serving a different working tree. An
orphaned dev server from a worktree once silently served stale code into every
measurement for a full round.
The contract
src/types.ts is the interface every subsystem codes against — ITrack,
IKart, IItems, IRace, IInput, Ctx, Surface, SURFACE_PROPS.
Do not edit src/types.ts as a side effect of another change. It is what
makes parallel work possible; changing it invalidates everyone else's
assumptions at once. If a change genuinely needs the contract widened, do that
as its own commit and say so.
Rough ownership, one concern per directory:
| path | what lives there |
|---|---|
src/render/ |
renderer, post chain, procedural textures/materials, sky |
src/world/ |
track layout + geometry, scenery, foliage, water |
src/kart/ |
chassis, suspension, tyres, model, liveries |
src/game/ |
race state, AI, camera, items, projectiles |
src/fx/ |
particles, trails, decals |
src/ui/ |
HUD, menus, minimap |
src/audio/ |
synthesis, music, engine |
src/core/ |
input, settings, diagnostics, prewarm, event bus |
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.
- 9d ago First seen · 191 lines · 2,881 tokens per session scan A 3659157ebd41
kart-royale CLAUDE.md is an instructions file published in the GitHub repository ryancampbell/kart-royale (60 stars, last pushed 1mo ago), licensed MIT. It adds 2,881 tokens to every session, about $0.0144 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.