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/zhangdszq/teamclaw/dev-test-workflowgit clone --depth 1 https://github.com/zhangdszq/teamclawWhat 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 | $0.00026 | $0.00724 |
| Opus 5 | $0.00013 | $0.00362 |
| Sonnet 5 | $0.00005 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
dev-test-workflow scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import json, base64, asyncio, websockets, urllib.request What it actually says
开发测试工作流
每次完成 UI / 功能开发后,按以下流程验证效果。
1. 编译验证(必须先通过)
# React + TypeScript 编译
cd /Users/zhang/git-repos/VK-Cowork && bun run build
# Electron 端编译
bun run transpile:electron
两条命令均 exit 0 才继续,否则先修复错误。
2. 重启应用
pkill -f electron 2>/dev/null; pkill -f vite 2>/dev/null
sleep 1 && npm run dev &
sleep 10 # 等待 Electron 窗口出现
3. Electron 调试端口截图
应用不带 --remote-debugging-port 时,用 Python CDP 直接连 9222(若需要则重启带端口):
# 带调试端口启动(替代 npm run dev)
pkill -f electron 2>/dev/null; pkill -f vite 2>/dev/null; sleep 1
bun run dev:react &
sleep 3 && npx electron . --remote-debugging-port=9222 &
sleep 6
# 截图脚本(保存至 screenshots/)
import json, base64, asyncio, websockets, urllib.request
async def screenshot(path="screenshots/test.png"):
# 获取页面列表
pages = json.loads(urllib.request.urlopen("http://localhost:9222/json").read())
ws_url = pages[0]["webSocketDebuggerUrl"]
async with websockets.connect(ws_url) as ws:
await ws.send(json.dumps({"id": 1, "method": "Page.enable"}))
await ws.recv()
await ws.send(json.dumps({"id": 2, "method": "Page.captureScreenshot", "params": {"format": "png"}}))
resp = json.loads(await ws.recv())
open(path, "wb").write(base64.b64decode(resp["result"]["data"]))
print(f"Screenshot: {path}")
asyncio.run(screenshot())
4. 激活窗口截全屏(备用方案)
osascript -e 'tell application "System Events" to tell process "Electron" to set frontmost to true'
sleep 1 && screencapture -o screenshots/test.png
5. 反复排查流程
遇到崩溃或渲染异常:
- 检查
better-sqlite3是否需要重编:npx electron-rebuild -f -w better-sqlite3 --electron-version 39.2.7 - 重启(步骤 2)→ 截图(步骤 3/4)→ 对比
注意
- CDP websocket URL 每次启动会变,从
http://localhost:9222/json动态获取 pip3 install websockets --break-system-packages(首次需要)- Vite dev server 地址:
http://localhost:5173,Electron 嵌入 API:http://localhost:2620
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.
- 2d ago First seen · 83 lines · 26 tokens per session scan A 1fac5d5e91a5
dev-test-workflow is a cursor rule published in the GitHub repository zhangdszq/teamclaw (113 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 724 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (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
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.