Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/xuliang2024/cutcli-cookbook/open-source-boundarygit clone --depth 1 https://github.com/xuliang2024/cutcli-cookbookWrote 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/rules/xuliang2024/cutcli-cookbook/open-source-boundary)<a href="https://agentmods.dev/rules/xuliang2024/cutcli-cookbook/open-source-boundary"><img src="https://agentmods.dev/badge/rules/xuliang2024/cutcli-cookbook/open-source-boundary.svg" alt="Measured on agentmods" 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 | $0.01585 | $0.01585 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade C, and why
open-source-boundary scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `replacements`：`npm install -g cut_cli` → `curl -s https://cutcli.com/cli | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `replacements`：`npm install -g cut_cli` → `curl -s https://cutcli.com/cli | bash` How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
开源 / 闭源边界（安全关键）
⚠ 这是本仓最重要的安全约束。违反任何一条都可能泄露 cutcli 闭源核心代码。
仓库定位
| 仓 | 路径 | 状态 |
|---|---|---|
cutcli-cookbook（本仓） |
/Users/m007/codes/cutcli-cookbook/ |
公开 GitHub: https://github.com/xuliang2024/cutcli-cookbook |
jy_cli |
/Users/m007/codes/jy_cli/ |
闭源 私有，不得泄露 |
四条铁律
1. 公开仓永远不出现这些路径的内容
| 闭源路径 | 包含的敏感内容 |
|---|---|
jy_cli/src/ |
TypeScript 源码、API 实现、内部模型 |
jy_cli/dist/ |
编译产物 |
jy_cli/binaries/ |
各平台二进制 |
jy_cli/worker/ |
cutcli.com 的 worker 实现 |
jy_cli/scripts/build-*.sh |
构建脚本 |
jy_cli/.env |
任何 .env 内容 |
✅ 公开仓自己的
worker/（即cutcli-cookbook/worker/）是 docs.cutcli.com 的反向代理，开源是合理的，不属于禁区。
2. 案例只调用公开 CLI 命令 cutcli xxx
- ✅ 允许：
cutcli draft create、cutcli captions add ... - ❌ 禁止：
import { addCaptions } from 'cut_cli/api/...' - ❌ 禁止：访问
~/.cut_cli/内部数据 - ❌ 禁止：直接读写剪映草稿 JSON 字段
3. 闭源 → 公开的内容流动只有一条路径
jy_cli/docs/cli.md, api.md, README.md (中文源)
jy_cli/docs/cli.en.md, api.en.md, README.en.md (英文源；TODO 待补)
↓
jy_cli/scripts/sync-to-cookbook.mjs (单向 + sanitizer + 双输出)
↓
cutcli-cookbook/docs/reference/{cli,api,concepts}.md ← 英文
cutcli-cookbook/docs/zh/reference/{cli,api,concepts}.md ← 中文
详见 jy_cli/scripts/sync.config.json。所有同步都过：
stripBlocks：删除<!-- internal -->...<!-- /internal -->段落stripBlocks：删除<!-- TODO-internal: ... -->单行replacements：cut <subcommand>→cutcli <subcommand>replacements：npm install -g cut_cli→curl -s https://cutcli.com/cli | bash
当前过渡态（cookbook 仓 i18n 已上线、闭源 sync 待升级）
闭源 sync 脚本目前只有中文输出。在它升级成双输出之前，本仓采取保底措施：
docs/reference/{cli,api,concepts}.md：暂时仍是中文，等闭源仓产出英文源后由 sync 覆盖docs/zh/reference/{cli,api,concepts}.md：直接是中文（PR 1 时从 root 复制过来）scripts/check-i18n-pairs.mjs把这三个文件加入SYNC_GENERATED白名单，跳过强制成对
闭源仓升级后：
jy_cli/docs/增加cli.en.md/api.en.md/README.en.md三份英文源jy_cli/scripts/sync-to-cookbook.mjs改成双输出，sync.test.mjs 增加双语用例- 跑
node scripts/sync-to-cookbook.mjs同时覆盖 cookbook 的 root 与 zh - 公开仓侧：把
SYNC_GENERATED白名单从check-i18n-pairs.mjs移除（双语都强制存在）
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.
- 4d ago First seen · 120 lines · 1,585 tokens per session scan C 04bec3cc423c
open-source-boundary is a cursor rule published in the GitHub repository xuliang2024/cutcli-cookbook (192 stars, last pushed 3mo ago), licensed MIT. It adds 1,585 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
generative-media-skills
Canonical instructions for generative-media-skills.
use-bun-instead-of-node-vite-npm-pnpm
../../CLAUDE.md.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.