Aller au contenu
TakoAPI
Retour aux skills

token-saver

par rubenaquispe

Coding Agents & IDEs
4.5kTéléchargements rapportés par clawskills.sh
9Étoiles
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Reduce OpenClaw AI costs with model-aware optimization.

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: optimize my workspace for the current model

AGENT
  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

SORTIE

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

Installation

clawhub install rubenaquispe/token-saver

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

Liens