they even resell GPT codex usage at 1~5% API costs. OpenAI has 1-month free trial promo in some regions, and they harvest free accounts in a large scale. I have a wechat contact that offers 98% off for GPT 5.5 and he's still profitable
- Prefer the most straightforward way of implementation.
- No defensive programming. Use try/except sparingly. Let most fatal errors propogate.
- No adding extra variables if there's not a clear reason to do so. Prefer simplicity
- Use comments sparingly. Function and variable names should be self-explaining and you don't need to comment most of the times
- If duplicate code is written, consider refactoring.
- DO NOT use getattr or isinstance or defensive programming patterns
- Do not create summary doc after completing a task, unless explicitly asked
- When you are asked to review git staged code changes, give feedback as if you are a senior tech lead ensuring high standards and rank the issues found with high/medium/low. Do not edit code or run git commands that manipulate the repo.
I fought with it hard during Sonnet 4.0 times. Some harnesses are actually not needed for latest model versions but I still keep these instructions.
I'm using it to manage product backend operations through Telegram. Without OpenClaw, most tasks were automatable with Claude Code anyways, but OpenClaw lets me to chat in TG and get things done without opening up a terminal.
As for security, I don't run OpenClaw on my machine, but I use a VPS and let Claude Code do security reviews regularly, and enforce OpenClaw to ask for confirmation every time it runs critical scripts or delete files.