Vai al contenuto
TakoAPI
Torna alle skill

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

di aeromomo

Coding Agents & IDEs
1.1kDownload riportati da clawskills.sh
0Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

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

Descrizione

Cosa fa questa skill

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.

Quando usarla

  • 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

Esempio di workflow

INPUT

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

AGENT
  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

OUTPUT

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

Installazione

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

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link