跳到正文
TakoAPI
返回技能列表

shed

由 compass-soul 提供

Coding Agents & IDEs
430下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Context window hygiene for long-running LLM agents.

描述

该技能的功能

Decision rules for managing context in long-running LLM agents. Covers when to mask tool outputs, trigger condensation, spawn sub-agents, or switch context as the window fills. Backed by NeurIPS 2025 and ACL 2024 research on context scaling and positional attention bias.

Simple observation masking halves cost and matches LLM summarization on solve rate, making it more effective than investing in complex compression pipelines.

何时使用

  • Cutting API costs during multi-hour coding agent runs
  • Preventing context overflow on large file analysis tasks
  • Designing multi-agent systems with clean context handoffs
  • Structuring agent memory for extended autonomous research
  • Diagnosing degraded agent behavior in long sessions

示例工作流

输入

User asks: An agent just returned 800 lines of grep output and context is at 65%. What should I do?

智能体
  1. 1

    Extract the relevant file paths and match counts from the grep output into a short summary

  2. 2

    Write that summary to a file for later reference

  3. 3

    Discard the raw tool output from context

  4. 4

    Check if context is still above 70% after masking

  5. 5

    If yes, mask the oldest reasoning turns from earlier in the session

输出

Context usage reduced, key facts preserved in a file, agent continues without compaction or loss of decision chain

安装

clawhub install compass-soul/shed

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接