← Back to Skills Marketplace
4742
Downloads
3
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-token-save
Description
Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling promp...
Usage Guidance
Safe to install as an advisory skill, but review any suggested config or memory changes before applying them. Back up openclaw.json and memory files, restrict memory-search/qmd paths to non-sensitive content, and enable heartbeat or subagents only if you want ongoing or parallel model calls.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-token-save
Version: 1.0.0
The skill instructs the OpenClaw agent to perform high-privilege actions, including locating and reading OpenClaw configuration files (e.g., `~/.openclaw/openclaw.json`), listing and proposing modifications to workspace files (`AGENTS.md`, `SOUL.md`, `MEMORY.md`), and auditing system cron and scheduled tasks. While the stated purpose is benign (token optimization), these capabilities (file system access, system-level auditing) are inherently risky and could be exploited if the agent's execution environment or interpretation of instructions were vulnerable, even without explicit malicious intent in the provided `SKILL.md` instructions.
Capability Assessment
Purpose & Capability
The skill's purpose is coherent: it audits OpenClaw token sources and recommends config, context, memory, model, heartbeat, cron, and subagent changes to reduce cost.
Instruction Scope
It asks the agent to locate config and workspace/memory files and provide patches or trimming guidance, but the artifacts frame these as user-reviewed recommendations rather than hidden automatic edits.
Install Mechanism
The package contains only Markdown files, no executable scripts, binaries, install hooks, or required environment variables.
Credentials
Reading OpenClaw config and workspace memory files is proportionate to token optimization; memory search/qmd examples can index local Markdown, so paths should be limited.
Persistence & Privilege
Heartbeat, compaction memory flush, qmd caching, and subagents are persistent or recurring behaviors, but they are clearly disclosed as optional optimization settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-token-save - After installation, invoke the skill by name or use
/openclaw-token-save - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
OpenClaw Token Optimizer initial release
- Audits OpenClaw token usage and provides configurable strategies to reduce token spend.
- Offers detailed guidance to trim workspace and memory files to shrink input context.
- Enables prompt caching, heartbeat, and context pruning to minimize redundant token use.
- Recommends efficient model tiering and use of subagents for lower-cost operations.
- Generates concrete config edits, file size targets, and a prioritized rollout plan.
Metadata
Frequently Asked Questions
What is OpenClaw Token Optimizer?
Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling promp... It is an AI Agent Skill for Claude Code / OpenClaw, with 4742 downloads so far.
How do I install OpenClaw Token Optimizer?
Run "/install openclaw-token-save" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw Token Optimizer free?
Yes, OpenClaw Token Optimizer is completely free (open-source). You can download, install and use it at no cost.
Which platforms does OpenClaw Token Optimizer support?
OpenClaw Token Optimizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw Token Optimizer?
It is built and maintained by ccjingeth (@ccjingeth); the current version is v1.0.0.
More Skills