İçeriğe geç
TakoAPI
Becerilere dön

shed

compass-soul tarafından

Coding Agents & IDEs
430İndirme sayıları clawskills.sh tarafından bildirilir
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

Context window hygiene for long-running LLM agents.

Açıklama

Bu Beceri Ne Yapar

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.

Ne Zaman Kullanılır

  • 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

Örnek İş Akışı

GİRİŞ

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

AJAN
  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

ÇIKIŞ

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

Kurulum

clawhub install compass-soul/shed

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar