Saltar al contenido
TakoAPI
Volver a skills

context-budgeting

por sarielwang93

Coding Agents & IDEs
2.1kDescargas según clawskills.sh
4Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information.

Descripción

Qué hace esta skill

A framework for managing context window usage in OpenClaw agents. It partitions context into defined zones (goals, history, decisions, background knowledge), checkpoints state before compaction, and runs a cleanup script to recover capacity without restarting the session.

Checkpointing to HOT_MEMORY.md before compaction preserves task state that standard compaction would otherwise discard, allowing the agent to resume accurately.

Cuándo usarla

  • Preventing memory loss during long multi-step coding sessions
  • Recovering task state after automatic context compaction
  • Reducing token costs on extended agent workflows
  • Managing multi-megabyte JSON outputs without flooding the context
  • Keeping long-running agents on track past the 80% context threshold

Flujo de trabajo de ejemplo

ENTRADA

User asks: Keep my refactoring task going after the context fills up

AGENTE
  1. 1

    Check current context usage via /status

  2. 2

    Confirm context exceeds 80% threshold

  3. 3

    Update memory/hot/HOT_MEMORY.md with current status, key decisions made, and next step

  4. 4

    Execute scripts/gc_and_checkpoint.sh to clear raw data and finalize compaction

  5. 5

    Resume the task using the checkpoint as the new working context

SALIDA

Task continues from the last checkpoint without losing prior decisions or progress

Instalación

clawhub install sarielwang93/context-budgeting

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

Enlaces