Saltar al contenido
TakoAPI
Volver a skills

zown-gemini-governor

por gtovd

Coding Agents & IDEs
758Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

A high-fidelity token management and model stabilization skill.

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

All pipeline stages completed without hitting Gemini TPM rate limits

Instalación

clawhub install gtovd/zown-gemini-governor

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces