token-saver
بواسطة rubenaquispe
Coding Agents & IDEsموجز
Reduce OpenClaw AI costs with model-aware optimization.
الوصف
ما الذي تفعله هذه المهارة
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.
متى تستخدمها
- 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
مثال على سير العمل
User asks: optimize my workspace for the current model
- 1
Detect active model and retrieve its context window from the local registry
- 2
Scan all workspace .md files and calculate token counts
- 3
Apply file-appropriate compression to USER.md and MEMORY.md
- 4
Set compaction threshold to 60% of the detected context window
- 5
Create .backup files for all modified documents
Compressed workspace files with auto-backups, compaction threshold set dynamically to model context size
التثبيت
clawhub install rubenaquispe/token-saverشغّل أمر واجهة سطر الأوامر، أو الصق النص في Claude Code أو Cursor أو Codex أو أي وكيل برمجة تستخدمه.