본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

token-saver

rubenaquispe 제작

Coding Agents & IDEs
4.5kclawskills.sh가 보고한 다운로드 수
9스타
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

Reduce OpenClaw AI costs with model-aware optimization.

설명

이 스킬이 하는 일

Reduces AI API costs by compressing workspace files (SOUL.md, USER.md, MEMORY.md, etc.) that are sent with every API call. Detects the active model and adapts compaction thresholds to its actual context window size. Supports 24+ models including Claude, GPT-4, Gemini, and DeepSeek.

Dynamic presets scale compaction thresholds to each model's actual context window, so the same preset works correctly whether you're on GPT-4o's 128K or Gemini's 1M context.

사용 시점

  • Cutting API costs on long agent sessions with large workspace files
  • Auditing which workspace files consume the most tokens before a project
  • Setting automatic chat compaction thresholds matched to the active model
  • Compressing MEMORY.md and USER.md into dense key-value format
  • Reverting workspace files to their pre-compression state after testing

예시 워크플로

입력

User asks: optimize my workspace for the current model

에이전트
  1. 1

    Detect active model and retrieve its context window from the local registry

  2. 2

    Scan all workspace .md files and calculate token counts

  3. 3

    Apply file-appropriate compression to USER.md and MEMORY.md

  4. 4

    Set compaction threshold to 60% of the detected context window

  5. 5

    Create .backup files for all modified documents

출력

Compressed workspace files with auto-backups, compaction threshold set dynamically to model context size

설치

clawhub install rubenaquispe/token-saver

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크