Aller au contenu
TakoAPI
Retour aux skills

shed

par compass-soul

Coding Agents & IDEs
430Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Context window hygiene for long-running LLM agents.

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

AGENT
  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

SORTIE

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

Installation

clawhub install compass-soul/shed

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens