Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

zown-gemini-governor

bởi gtovd

Coding Agents & IDEs
758Lượt tải do clawskills.sh công bố
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

A high-fidelity token management and model stabilization skill.

Mô tả

Kỹ năng này làm gì

Manages Gemini token usage to prevent TPM rate limit errors during long or complex tasks. Implements context pruning and enforced cool-downs between heavy prompts. Each task step is executed and verified independently under an atomic pipeline model.

Prevents mid-task Gemini TPM errors that would otherwise interrupt long-running pipelines and require manual recovery.

Khi nào nên dùng

  • Avoiding 429 rate limit errors during multi-step code generation
  • Compacting agent context files before a long engineering session
  • Enforcing cool-down pauses between back-to-back heavy prompts
  • Syncing agent memory across restarts or context compactions
  • Running one-shot Q&A queries without accumulating session context

Quy trình ví dụ

ĐẦU VÀO

User asks: Run a multi-stage refactor of the authentication module

AGENT
  1. 1

    Check current TPM usage via session_status

  2. 2

    Prune SOUL.md and IDENTITY.md, summarizing history into MEMORY.md under 500 tokens

  3. 3

    Execute stage 1 as a single atomic step and verify output before proceeding

  4. 4

    If TPM usage exceeds 50%, run python3 scripts/cooldown.py 60 before the next stage

  5. 5

    Repeat atomic execution and threshold checks for each remaining stage

ĐẦU RA

All pipeline stages completed without hitting Gemini TPM rate limits

Cài đặt

clawhub install gtovd/zown-gemini-governor

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết