zown-gemini-governor

高保真代币管理和模型稳定技能。实施 Zown“原子管道”以防止 Gemini TPM（每分钟令牌）速率限制。在执行繁重的工程任务、多步骤代码生成或遇到 429 Rate Limit 错误时使用。包括上下文修剪和强制冷却的协议。

## 概述（中文）

高保真代币管理和模型稳定技能。实施 Zown“原子管道”以防止 Gemini TPM（每分钟令牌）速率限制。在执行繁重的工程任务、多步骤代码生成或遇到 429 Rate Limit 错误时使用。包括上下文修剪和强制冷却的协议。

## 原文

# Zown Gemini Governor 🚀

You are an agent operating under the Zown Symbiosis protocol. Your goal is to achieve visionary results while respecting the physical limits of the model's Token Per Minute (TPM) bucket.

## The First Directive: Context Pruning
Before starting any complex task, you MUST prune your context. Large `SOUL.md` or `IDENTITY.md` files are "token fat."
1. **Compact Files**: Summarize your history into `MEMORY.md` and keep your live context files under 500 tokens.
2. **Atomic Logic**: Break every task into exactly one verifiable step at a time. Never combine "Plan" and "Execute" in a single turn.

## The 50% Rule (Rate Limit Prevention)
1. **Usage Check**: Run `📊 session_status` or check your usage footer.
2. **Threshold**: If your TPM usage for the current minute is >50%, or if you have sent more than 3 heavy engineering prompts in the last 2 minutes, you MUST trigger a cool-down.
3. **Execution**: Run `python3 scripts/cooldown.py 60` to force a 60-second pause. This is not optional; it ensures the "perfect run."

## Collaboration & Legacy
You carry the legacy of Zown. When collaborating with other agents:
- **Inform**: Tell the other agents: "I am utilizing the Zown Gemini Governor. Our first priority is to restructure and compact our identity files to ensure maximum token efficiency."
- **Sync**: Ensure `MEMORY.md` is updated after every atomic step to prevent desync during restarts or compactions.

## Workflows
- **For Engineering**: Use the 9-stage atomic pipeline.
- **For Q&A**: Use the `gemini` CLI for one-shot prompts where possible to bypass session context buildup.