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.
curl -O https://raw.githubusercontent.com/ksgisang/AI-Watch-Tester/main/CLAUDE.mdgit clone --depth 1 https://github.com/ksgisang/AI-Watch-TesterWrote 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/ksgisang/ai-watch-tester/claude-md)<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.
<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>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 | $0.33827 | $0.33827 |
| Opus 5.5 | $0.13531 | $0.13531 |
| Sonnet 5.5 | $0.06765 | $0.06765 |
| Haiku 4.5 | $0.03383 | $0.03383 |
Grade C, and why
AI-Watch-Tester CLAUDE.md scanned grade C with 3 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **도구 자신이 커밋되지 않은 수리를 지웠습니다**: 역변이 보조기의 원본 사본은 `if not dst.exists()`로만 복사하므로, 지난 세션이 남긴 사본은 **지금 소스보다 낡았습니다**. `restore()`가 그것을 덮어써 `run_cmd.py`의 수리가 조용히 되돌아갔습니다(`grep`으로 발견). **AAT-121의 `git checkout --` 교훈이 보조기에도 그대로 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. 디렉터리 `Uses a credential from the user's machine` **잔여 2건** — **고치기 전에 먼저 펼쳐서 어느 두 자리인지 확인할 것.** 포털 권고(`user_config` + `sensitive: true`)를 그대로 받으면 **거짓을 선언하게 됩니다**: stdio MCP 서버는 자격증명을 읽지 않습니다(`mcp/server.py`는 `os.envi Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- *"It never runs a shell"* 이 **거짓**이었습니다 — `mcp/server.py:104`가 `os.system(f"which ...")`를 돌리고 있었습니다. 그런데 그 `_find_aat()`는 **아무 데서도 호출되지 않고**, 둘째 분기는 `create_subprocess_exec`의 `argv[0]`이 될 수 없는 `"python -m aat"`를 반환합니다. The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 Changed · +1 lines · +275 tokens per session 9f71f0566334
- 13d ago Changed · +11 lines · +423 tokens per session 6c48e5891545
- 14d ago Changed · +77 lines · +7,248 tokens per session 00f84a219774
- 15d ago Changed · +27 lines · +3,204 tokens per session scan A → C b945e0eb3072
- 20d ago Changed · +16 lines · +1,884 tokens per session a28951052e41
- 22d ago Changed · +54 lines · +4,935 tokens per session c14412d7f8fb
- 26d ago Changed · +130 lines · +8,813 tokens per session 017510e79f9a
- 1mo ago Changed · +7 lines · +376 tokens per session 37c9e35ec2fe
- 1mo ago Changed · +22 lines · +744 tokens per session 819b7ade6ed4
- 2mo ago First seen · 367 lines · 5,925 tokens per session scan A dffb9ff09bf6
AI-Watch-Tester CLAUDE.md is an instructions file published in the GitHub repository ksgisang/AI-Watch-Tester (7 stars, last pushed 10d ago), licensed AGPL-3.0. It adds 33,827 tokens to every session, about $0.1353 per session on Opus 5.5. A static security scan graded it C with 3 findings (recursive force delete, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
qmax-mcp copilot-instructions.md
Copilot instructions for Quality-Max/qmax-mcp, covering qualitymax qa workflow and adjacent tools.
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).
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.
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).
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 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).