✓ Verified 💻 Development ✓ Enhanced Data

Token Saver

Reduce OpenClaw AI costs with model-aware optimization.

Rating
4.2 (224 reviews)
Downloads
11,581 downloads
Version
1.0.0

Overview

Reduce OpenClaw AI costs with model-aware optimization.

Complete Documentation

View Source →

Token Saver v3

💡 Did you know? Every API call sends your workspace files (SOUL.md, USER.md, MEMORY.md, AGENTS.md, etc.) along with your message. These files count toward your context window, slowing responses and costing real money on every message.

Token Saver v3 is model-aware — it knows your model's context window and adapts recommendations accordingly. Using Gemini's 1M context? Presets scale up. On GPT-4o's 128K? Presets adjust down.

What's New in v3

Featurev2v3
Compaction presetsFixed (80K/120K/160K)Dynamic (% of model's context)
Model detectionFragile, env-onlyRobust fallback chain
Context windowsNot trackedFull registry (9 models)
Model infoHardcoded pricingJSON registry, easy updates
Already-optimizedRe-compressedSmart bypass

Commands

CommandWhat it does
/optimizeFull dashboard — files, models, context usage %
/optimize tokensCompress workspace files (auto-backup)
/optimize compactionChat compaction control (model-aware)
/optimize compaction balancedApply balanced preset (60% of context)
/optimize compaction 120Custom threshold (compact at 120K)
/optimize modelsDetailed model audit with registry
/optimize revertRestore backups, disable persistent mode

Features

📊 Model-Aware Dashboard

Shows current model, context window, and usage percentage:
text
🤖 Model: Claude Opus 4.5 (200K context)
   Detected: openclaw.json

📊 Context Usage: [████████░░░░░░░░░░░░] 42% (84K/200K)

📁 Workspace File Compression

Scans all .md files, shows token count and potential savings. Smart bypass skips already-optimized files.

File-aware compression:

  • SOUL.md — Light compression, keeps personality language
  • AGENTS.md — Medium compression, dense instructions
  • USER.md / MEMORY.md — Heavy compression, key:value format
  • PROJECTS.md — No compression (user structure preserved)

💬 Dynamic Compaction Presets

Presets adapt to your model's context window:

Preset% of ContextClaude 200KGPT-4o 128KGemini 1M
Aggressive40%80K51K400K
Balanced60%120K77K600K
Conservative80%160K102K800K
Off95%190K122K950K

🤖 Model Registry

24+ models with context windows, pricing, and aliases:
  • Claude: Opus 4.6 (1M), Opus 4.5, Sonnet 4.5, Sonnet 4, Haiku 4.5, Haiku 3.5 (200K)
  • OpenAI: GPT-5.2, GPT-5.1, GPT-5-mini, GPT-5-nano (256K), GPT-4.1, GPT-4o (128K), o1, o3, o4-mini
  • Gemini: 3 Pro (2M), 2.5 Pro, 2.0 Flash (1M)
  • Others: DeepSeek V3 (64K), Kimi K2.5 (128K), Llama 3.3 70B, Mistral Large

🔍 Robust Model Detection

Detection priority:
  • Runtime injection (--model=...)
  • Environment variables (SKILL_MODEL, OPENCLAW_MODEL)
  • Config file (~/.openclaw/openclaw.json)
  • File inference (TOOLS.md, MEMORY.md mentions)
  • Fallback: Claude Sonnet 4 (safe default)
Unknown model handling:
  • Strict version matching — opus-6.5 won't fuzzy-match to opus-4.5
  • Unknown models get safe defaults (200K context) + warning
  • Easy to add new models to scripts/models.json

📝 Persistent Mode

Adds writing guidance to AGENTS.md for continued token efficiency:

FileWriting Style
SOUL.mdEvocative, personality-shaping
AGENTS.mdDense instructions, symbols OK
USER.mdKey:value facts
MEMORY.mdUltra-dense data

Safety

  • Auto-backup — All modified files get .backup extension
  • Integrity > Size — Never sacrifices meaning for smaller tokens
  • Smart bypass — Skips already-optimized files
  • Revert anytime — /optimize revert restores everything
  • No external calls — All analysis runs locally

Installation

text
clawhub install token-saver --registry "https://www.clawhub.ai"

Version History

  • 3.0.0 — Model registry, dynamic presets, robust detection, smart bypass
  • 2.0.1 — Chat compaction, file-aware compression, persistent mode
  • 1.0.0 — Initial release

Installation

Terminal bash 

openclaw install token-saver
Copied!

💻Code Examples

Shows current model, context window, and usage percentage:

shows-current-model-context-window-and-usage-percentage.txt
🤖 Model: Claude Opus 4.5 (200K context)
   Detected: openclaw.json

📊 Context Usage: [████████░░░░░░░░░░░░] 42% (84K/200K)

Tags

#coding_agents-and-ides

Quick Info

Category Development
Model Claude 3.5
Complexity One-Click
Author rubenaquispe
Last Updated 3/10/2026
🚀
Optimized for
Claude 3.5
🧠

Ready to Install?

Get started with this skill in seconds

openclaw install token-saver

Resources

📂
OpenClaw Skills
View on OpenClaw GitHub
→

Related Skills

✓ Verified 💻 Development

4claw

4claw — a moderated imageboard for AI agents.

🧠 Claude-Ready #ai_and-llms
)}
★ 4.4 (118)
↓ 4,990
v1.0.0
✓ Verified 💻 Development

Aap Passport

Agent Attestation Protocol - The Reverse Turing Test.

🧠 Claude-Ready #ai_and-llms
)}
★ 4.3 (89)
↓ 4,621
v1.0.0
✓ Verified 💻 Development

Acestep Lyrics Transcription

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API.

⚡ GPT-Optimized #ai_and-llms #api #script
)}
★ 3.8 (274)
↓ 17,648
v1.0.0
✓ Verified 💻 Development

Adaptive Suite

A continuously adaptive skill suite that empowers Clawdbot.

🧠 Claude-Ready #ai_and-llms #bot
)}
★ 4.7 (88)
↓ 1,625
v1.0.0