本文へスキップ
TakoAPI
スキル一覧に戻る

shed

compass-soul 作

Coding Agents & IDEs
430ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Context window hygiene for long-running LLM agents.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

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

エージェント
  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

出力

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

インストール

clawhub install compass-soul/shed

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク