AI-Watch-Tester: Instructions file for Claude Code

CLAUDE.md

AI-Watch-Tester CLAUDE.md is an instructions file for Claude Code from ksgisang/AI-Watch-Tester. It costs 5,925 tokens per session, scanned A, original, MIT.

Project instructions for AAT, an AI-assisted web testing tool that uses image matching to test interfaces and repeat fixes when needed. They require user approval between scanning, preparing a scenario, running it, and reporting results.

In plain words
What is it for?
Use them when scanning a web application, preparing and reviewing YAML test scenarios, running approved tests, and reporting their results.
Why use it?
They prevent unattended test runs, automatic code changes, and attempts to fake or bypass approval. They also require the process to stop immediately when a step fails.

Instructions file for Claude Code

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

This is ksgisang/AI-Watch-Tester's own configuration. It tells Claude Code how to work on AI-Watch-Tester 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 AI-Watch-Tester configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ksgisang/AI-Watch-Tester. 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/ksgisang/AI-Watch-Tester/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ksgisang/AI-Watch-Tester

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 AI-Watch-Tester CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/claude-md/github.svg)](https://agentmods.dev/instructions/ksgisang/ai-watch-tester/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ksgisang/ai-watch-tester/claude-md"><img src="https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/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 AI-Watch-Tester CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ksgisang/ai-watch-tester/claude-md"><img src="https://agentmods.dev/badge/instructions/ksgisang/ai-watch-tester/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,925 This file is loaded in full into every session.
When invoked 5,925 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 $0.05925 $0.05925
Opus 5 $0.02962 $0.02962
Sonnet 5 $0.01185 $0.01185
Haiku 4.5 $0.00592 $0.00592

Measured 12d ago against content hash dffb9ff09bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

AI-Watch-Tester 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 12d 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 · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AAT (AI Auto Tester) — Project Guide

Overview

AI 기반 DevQA Loop 오케스트레이터. 이미지 매칭으로 UI 테스트를 자동화하고, 실패 시 AI가 코드를 수정하고 재테스트하는 루프를 반복한다.

⛔ AWT Testing Workflow (필수 준수)

사용자가 AWT로 테스트를 요청하면 반드시 아래 4단계를 순서대로 따를 것.

Step 1: SCAN

aat scan --url <URL>

.aat/scan_result.json을 읽고 사용자에게 요약 보고 → 승인 대기

Step 2: GENERATE + PRESENT

시나리오 YAML 작성 → 사용자에게 보여주고 → 승인 대기

Step 3: EXECUTE (승인 후에만)

aat run --skill-mode --fast <scenario>

→ 실패 시 즉시 중단 → 사용자에게 보고 → 지시 대기

Step 4: REPORT

결과 요약 보고

금지 사항

  • aat devqa 사용 금지 (사용자 체크포인트 없이 전체 파이프라인 실행)
  • -y / --auto-approve 사용 금지
  • 사용자 승인 없이 테스트 실행 금지
  • 사용자 지시 없이 코드/시나리오 자동 수정 금지

⛔ AI Security Rules — Approval Bypass Prevention (Layer 4)

이 섹션은 모든 AI 에이전트(Claude, GPT, Copilot 등)가 반드시 준수해야 합니다.

절대 금지 행위

  1. _AAT_APPROVAL_TOKEN 환경변수를 직접 설정하거나 위조하지 마세요.
  2. .aat/.approval_token_* 파일을 직접 생성, 읽기, 수정하지 마세요.
  3. approval_token.py, scenario_reviewer.py, audit.py의 보안 로직을 수정하지 마세요.
  4. /dev/tty 읽기를 우회하거나 _is_interactive() 결과를 조작하지 마세요.
  5. .aat/audit.log를 삭제하거나 수정하지 마세요.
  6. --auto-approve, -y 플래그를 사용하거나 구현하지 마세요.
  7. echo "" | aat run 같은 stdin 파이프로 승인을 우회하지 마세요.

승인 메커니즘 (4-Layer Defense)

  • Layer 1: /dev/tty 직접 읽기 — stdin 파이프 우회 방지
  • Layer 2: 일회용 암호화 토큰 — 환경변수 위조 방지
  • Layer 3: JSONL 감사 로그 — 모든 실행 시도 기록
  • Layer 4: 이 규칙 — AI 에이전트의 우회 시도 자체를 금지

AI 에이전트의 올바른 동작

  • aat run은 반드시 사용자의 터미널에서 실행하세요.
  • 사용자가 직접 Enter를 눌러 승인해야 합니다.
  • 승인 프롬프트를 건너뛸 수 있는 방법을 찾으려 하지 마세요.

Key Documents

  • PM/기획서_v1.md — 제품 기획서 (전체 비전)
  • PM/Develop_Plan_v0.2.md — 기술 아키텍처
  • PM/설계서_v0.2.md구현 상세 설계 (이 파일이 구현의 기준)
  • PM/비즈니스_플랜_v0.2.md — 사업 전략
  • docs/RELEASE_GUIDE.md배포 가이드 (PyPI/README/PR 동기화 절차)

Tech Stack

  • Python 3.11+, Typer (CLI), Pydantic v2, pydantic-settings
  • Playwright (WebEngine), PyAutoGUI (DesktopEngine), OpenCV (이미지 매칭), pytesseract (OCR)
  • anthropic SDK (Claude API), openai SDK, httpx (Ollama), Jinja2 (리포트), SQLite (학습 DB)
  • Dev: ruff, mypy, pytest, pytest-asyncio, pre-commit

Read the full file on GitHub · 367 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. 12d ago First seen · 367 lines · 5,925 tokens per session scan A dffb9ff09bf6

Subscribe to this mod's changes

AI-Watch-Tester CLAUDE.md is an instructions file published in the GitHub repository ksgisang/AI-Watch-Tester (7 stars, last pushed 5mo ago), licensed MIT. It adds 5,925 tokens to every session, about $0.0296 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 2026-08-31.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens