Перейти к содержимому
TakoAPI
Назад к навыкам

context-budgeting

от sarielwang93

Coding Agents & IDEs
2.1kЧисло загрузок по данным clawskills.sh
4Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

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

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

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

АГЕНТ
  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

ВЫВОД

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

Установка

clawhub install sarielwang93/context-budgeting

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки