功能描述

Reduce OpenClaw AI costs with model-aware optimization. Features dynamic compaction presets based on your model's context window, intelligent file compression, and robust model detection with fallback. Supports Claude, GPT-4, Gemini, DeepSeek, and more.

使用说明 (SKILL.md)

Token Saver v3

Name: Token Saver
Author: rubenaquispe

💡 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

Feature	v2	v3
Compaction presets	Fixed (80K/120K/160K)	Dynamic (% of model's context)
Model detection	Fragile, env-only	Robust fallback chain
Context windows	Not tracked	Full registry (9 models)
Model info	Hardcoded pricing	JSON registry, easy updates
Already-optimized	Re-compressed	Smart bypass

Commands

Command	What it does
`/optimize`	Full dashboard — files, models, context usage %
`/optimize tokens`	Compress workspace files (auto-backup)
`/optimize compaction`	Chat compaction control (model-aware)
`/optimize compaction balanced`	Apply balanced preset (60% of context)
`/optimize compaction 120`	Custom threshold (compact at 120K)
`/optimize models`	Detailed model audit with registry
`/optimize revert`	Restore backups, disable persistent mode

Features

📊 Model-Aware Dashboard

Shows current model, context window, and usage percentage:

🤖 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 Context	Claude 200K	GPT-4o 128K	Gemini 1M
Aggressive	40%	80K	51K	400K
Balanced	60%	120K	77K	600K
Conservative	80%	160K	102K	800K
Off	95%	190K	122K	950K

🤖 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:

File	Writing Style
SOUL.md	Evocative, personality-shaping
AGENTS.md	Dense instructions, symbols OK
USER.md	Key:value facts
MEMORY.md	Ultra-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

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

安全使用建议

Use caution before installing or invoking `/optimize tokens`. The local/no-external-calls design is a positive sign, but this skill can change AGENTS.md, MEMORY.md, USER.md, and SOUL.md in ways that affect future agent behavior. If you proceed, back up your workspace, run only in a test copy first, inspect every diff, and avoid accepting persistent-mode changes unless you understand them.

功能分析

Type: OpenClaw Skill Name: token-saver Version: 3.0.0 The skill is classified as suspicious due to its use of prompt injection and persistence mechanisms, despite these being disclosed and intended for benign token optimization. Specifically, `scripts/compressor.js` contains hardcoded instructions like 'Auto-execute.' and 'Internal actions (read/organize/learn): free' that directly influence agent behavior. Furthermore, `scripts/optimizer.js` modifies `AGENTS.md` to enable a 'Persistent Mode' by appending writing guidance, which is a form of persistence and prompt injection. While these actions are disclosed in `SKILL.md` and `audit.json` and align with the stated purpose of cost reduction, they represent high-risk capabilities that modify core agent instructions.

能力评估

⚠ Purpose & Capability

Optimizing token usage is coherent with reading and compressing workspace Markdown, but the provided compressor includes hardcoded AGENTS.md content that is not merely a compressed version of the user's existing file.

⚠ Instruction Scope

The hardcoded AGENTS.md template includes behavior-shaping instructions such as auto-execution, memory maintenance, heartbeats, and proactive checks, which are broader than a token optimization workflow.

ℹ Install Mechanism

There is no install spec or dependency install path, but the source is listed as unknown and the package contains runnable Node scripts, so users should verify provenance before use.

⚠ Credentials

The skill scans workspace Markdown files and appears to auto-scan chat/session history for recommendations; the local-only design is mitigating, but the scope is sensitive and not clearly bounded in the main documentation.

⚠ Persistence & Privilege

The skill documents persistent mode and code shows generation of persistent AGENTS.md instructions; modifying agent memory/config files can affect future sessions even after the original command is complete.

版本历史

v3.0.0

v3: Model-aware optimization with dynamic presets, robust model detection, context window registry for 9+ models

v2.0.1

Added back intro text explaining why token optimization matters

v2.0.0

Chat compaction with personalized recommendations, file-aware compression, persistent mode with file-type writing styles

v1.1.0

Persistent Mode - AI maintains compressed format after optimization. One-and-done, reversible with /optimize revert.

v1.0.2

Fix model detection to read actual OpenClaw config, rename dashboard to Token Saver

v1.0.1

Add educational intro about workspace file token overhead

v1.0.0

Initial release - dashboard with file compression and AI model audit

元数据

Slug token-saver

版本 3.0.0

许可证 —

累计安装 32

当前安装数 31

历史版本数 7

常见问题

Token Saver 是什么？

Reduce OpenClaw AI costs with model-aware optimization. Features dynamic compaction presets based on your model's context window, intelligent file compression, and robust model detection with fallback. Supports Claude, GPT-4, Gemini, DeepSeek, and more. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 6432 次。

如何安装 Token Saver？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install token-saver」即可一键安装，无需额外配置。

Token Saver 是免费的吗？

是的，Token Saver 完全免费（开源免费），可自由下载、安装和使用。

Token Saver 支持哪些平台？

Token Saver 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Token Saver？

由 Ruben Quispe（@rubenaquispe）开发并维护，当前版本 v3.0.0。

Token Saver