本文へスキップ
TakoAPI
スキル一覧に戻る

cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction

aeromomo 作

Coding Agents & IDEs
1.1k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

Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation.

説明

このスキルでできること

Compresses AI agent workspace files, including memory, session transcripts, and sub-agent context, using 5 layered techniques: rule-based dedup, dictionary encoding, observation extraction, RLE patterns, and format optimization. All compression is deterministic and runs without LLM calls. Session transcripts compress ~97%; first-run savings typically reach 50%+.

All compression runs locally without LLM calls, so there is no additional API cost to reduce token spend.

使いどころ

  • Reducing token costs on long-running Claude agent sessions
  • Compressing accumulated session transcripts before starting a new project
  • Running weekly maintenance on AI agent memory files via cron
  • Shrinking sub-agent context payloads before handoff
  • Auditing workspace token usage before a billing cycle

ワークフロー例

入力

User asks: compress my Claude agent workspace to cut token costs

エージェント
  1. 1

    Run benchmark command to preview savings without modifying any files

  2. 2

    Execute full pipeline to apply all 5 compression layers in sequence

  3. 3

    Convert session JSONL transcripts to structured observation summaries

  4. 4

    Generate L0/L1/L2 tiered summaries for progressive context loading

  5. 5

    Save codebook to memory/.codebook.json for future decompression

出力

Workspace compressed 50%+ overall; session transcripts reduced ~97%; tiered summary files written to memory/

インストール

clawhub install aeromomo/cut-your-tokens-97percent-savings-on-session-transcripts-via-observation-extraction

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