frogger: Instructions file for Claude Code

CLAUDE.md

frogger CLAUDE.md is an instructions file for Claude Code from ultra-ai-dle/frogger. It costs 1,136 tokens per session, scanned A, original, MIT.

A project instruction file describing Prova, an AI-assisted algorithm visualisation debugger, its technologies, directory layout, execution pipeline, and AI integration rules. It gives an agent repository-specific context rather than adding a user-facing feature.

In plain words
What is it for?
Use it as background when an agent works on this repository's Next.js interface, code execution workers, APIs, visualisations, state store, documentation, or AI providers.
Why use it?
Agents can make incorrect changes when they do not know how a repository is structured or which system owns each responsibility. These instructions establish the project's expected boundaries and workflow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is ultra-ai-dle/frogger's own configuration. It tells Claude Code how to work on frogger itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything frogger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ultra-ai-dle/frogger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ultra-ai-dle/frogger/develop/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ultra-ai-dle/frogger

Made for: Claude Code.

Wrote 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.

agentmods badge for frogger CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ultra-ai-dle/frogger/claude-md/github.svg)](https://agentmods.dev/instructions/ultra-ai-dle/frogger/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ultra-ai-dle/frogger/claude-md"><img src="https://agentmods.dev/badge/instructions/ultra-ai-dle/frogger/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.

agentmods 80×15 button for frogger CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ultra-ai-dle/frogger/claude-md"><img src="https://agentmods.dev/badge/instructions/ultra-ai-dle/frogger/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,136 This file is loaded in full into every session.
When invoked 1,136 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01136 $0.01136
Opus 5.5 $0.00454 $0.00454
Sonnet 5.5 $0.00227 $0.00227
Haiku 4.5 $0.00114 $0.00114

Measured 27d ago against content hash 06a2857e644b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frogger 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 27d 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project: Prova

AI 기반 알고리즘 시각화 디버거. 브라우저에서 코드를 실행하고, AI가 실행 흐름을 시각화 + 자연어 해설로 변환한다. 핵심 철학: 역할 분리 — 실행의 정확성은 엔진이, 해석과 설명은 AI가, 디자인은 프론트엔드가 전담.

Tech Stack

  • Framework: Next.js (App Router), React, Tailwind CSS
  • State: Zustand (단일 스토어)
  • Visualization: D3, Three.js
  • Execution: Pyodide (Python WASM), Acorn (JS AST 계측), Web Worker, Java 원격 실행 서버
  • AI: Gemini/OpenAI/Groq/Anthropic/OpenRouter (멀티 프로바이더 폴백)

Directory Structure

app/
├── api/analyze/     # AI: 알고리즘 분류 + 전략 결정
├── api/java/execute/ # Java 원격 실행 프록시
├── page.tsx         # 메인 페이지
src/
├── config/          # 실행 제한 설정 (timeout, maxSteps)
├── features/
│   ├── execution/   # Worker 라이프사이클 (ProvaRuntime)
│   ├── trace/       # rawTrace + AI 어노테이션 → mergedTrace 병합
│   ├── playback/    # 재생/탐색 컨트롤
│   └── visualization/  # GridLinearPanel, GraphPanel, 3D Volume
├── lib/             # AI 프로바이더, 태그 정규화, 피벗 보강
├── store/           # Zustand 스토어 (useProvaStore)
├── types/           # 파이프라인 전체 타입 (prova.ts)
public/worker/       # pyodide.worker.js, js.worker.js
docs/                # 개발자 아키텍처 문서
prompts/             # AI에게 던질 프롬프트 모음 (UI, pitch, 언어 확장)

3-Step Pipeline

  1. TRACE — Worker(Pyodide/JS) 또는 원격 JVM(Java)이 코드 실행 + trace 수집 → {rawTrace, branchLines, varTypes}
  2. AI — /api/analyze(알고리즘 분류·전략·변수 매핑·enrichment)
  3. RENDER — mergedTrace[currentStep] 기준으로 시각화 패널 렌더링

AI Integration Rules

  • AI 분류 규칙: 역할은 타입/이름이 아닌 사용 패턴으로만 결정 (상세: app/api/analyze/CLAUDE.md)
  • var_mapping[].var_name은 반드시 실제 varTypes 키여야 함
  • aiError 키 이름 고정 (error, analysisError 등 사용 금지)
  • AI는 action 이름 + params만 반환, 색상/스타일 절대 포함 금지

Custom Commands

  • /qa — feature별 QA 체크리스트 생성/업데이트
  • /test — feature별 테스트 작성 + 커밋
  • /review — feature + test 코드 품질 검사 + 커밋
  • /docs — 아키텍처 문서 + JSDoc + 인라인 주석 업데이트
  • /trace-validate — trace 스키마 + 병합 무결성 검증
  • /prompt-diff — AI 프롬프트 변경 회귀 체크
  • /refactor-audit — export 타입/시그니처 호환성 검증
  • /pr-ready — lint + type check + build + 변경 요약

Read the full file on GitHub · 84 lines

Changes

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.

  1. 27d ago First seen · 84 lines · 1,136 tokens per session scan A 06a2857e644b

Subscribe to this mod's changes

frogger CLAUDE.md is an instructions file published in the GitHub repository ultra-ai-dle/frogger (8 stars, last pushed 6mo ago), licensed MIT. It adds 1,136 tokens to every session, about $0.0045 per session on Opus 5.5. 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 2026-10-02.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens