Borrowing it
Nothing to install: this file belongs to sindney/fury3d. 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/sindney/fury3d/master/CLAUDE.mdgit clone --depth 1 https://github.com/sindney/fury3dWrote 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/sindney/fury3d/claude-md)<a href="https://agentmods.dev/instructions/sindney/fury3d/claude-md"><img src="https://agentmods.dev/badge/instructions/sindney/fury3d/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/sindney/fury3d/claude-md"><img src="https://agentmods.dev/badge/instructions/sindney/fury3d/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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
fury3d 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 today.
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.
What it actually says
CLAUDE.md
Notes for Claude Code (and other coding agents) working in this repo.
Code style: comments
Write code as if it was always correct, then stop.
- No history in comments. No "previously X did Y so now we do Z", no "this fixes a bug where...", no "legacy" or "new" labels on code paths. The current code is the code.
- One-liners or none. Either a short single-line note above a non-obvious line, or no comment at all. Don't restate what the API name already says. No multi-paragraph essays.
- Drop workarounds, then forget. When removing a workaround, don't leave a comment explaining what it replaced. The replacement is self-evident from the code.
- Rename, don't annotate. If a function name no longer reflects what it does, rename it. Don't keep the stale name and add a comment.
- ASCII only. No em-dash, arrows, smart quotes, degree signs, multiplication sign, or ellipsis. Use
-,->,'...',deg,x,....
Code style: structure
- Match the surrounding code's density, naming, and idiom. Don't restyle adjacent code.
- Keep changes minimal and scoped to the task. No drive-by refactors.
- Comments are facts, not narratives. If a comment is needed, it states what the code does or why a non-obvious choice exists — not how the code was reached.
Working in this repo
- OpenSpec: changes live in
openspec/changes/<name>/withproposal.md,design.md,specs/,tasks.md. Useopenspec status --change <name> --jsonandopenspec instructions apply --change <name> --jsonto drive/opsx:apply. - Tests:
tests/lua/*.luainvoked headlessly via./fury exec <scene> <script.lua>fromexamples/. - Build dirs:
build/(normal),build-asan/(AddressSanitizer). Don't ship binaries from these —examples/furyandexamples/furyeare the outputs.
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.
- today First seen · 26 lines · 477 tokens per session scan A b3eaf3a2dc1c
fury3d CLAUDE.md is an instructions file published in the GitHub repository sindney/fury3d (90 stars, last pushed yesterday), licensed MIT. It adds 477 tokens to every session, about $0.0024 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 2026-09-15.
Other instructions, from other repositories
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).
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.
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.
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.
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).