← Back to Skills Marketplace
149
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install token-kill
Description
Reduce OpenClaw token consumption by 95%+ using three optimization techniques (slash commands, script-first principle, and model tiering)
Usage Guidance
This skill is guidance-only and appears coherent and low-risk. Before adopting: verify that the platform slash commands (/compress, /new, /stop, /restart) actually behave as described and won't delete or irreversibly prune needed data; when you implement the recommended scripts, store any service credentials securely (not in model prompts); test model-tier routing in a sandbox to ensure quality/latency trade-offs are acceptable; and run a billing/audit check after changes to confirm expected savings. If you need stronger guarantees, ask the skill author for concrete examples or scripts that you can review.
Capability Analysis
Type: OpenClaw Skill
Name: token-kill
Version: 0.0.1
The skill bundle contains only documentation and instructions (SKILL.md) focused on optimizing LLM token usage through standard practices like context compression, model tiering, and offloading mechanical tasks to scripts. There is no executable code, no data exfiltration logic, and no malicious prompt injection intended to subvert the agent's security or access sensitive information.
Capability Assessment
Purpose & Capability
The name and description promise token-cost reductions and the SKILL.md contains only recommendations (slash commands, script-first, model tiering) that directly align with that goal. There are no unrelated required binaries, env vars, or installs.
Instruction Scope
All runtime instructions are procedural recommendations (use /new, /compress, prefer scripts, route workloads to cheaper models). The file references (e.g., memory.md) are conceptual and the skill does not instruct the agent to read arbitrary files, exfiltrate data, or call unexpected external endpoints.
Install Mechanism
No install spec or code files are included; this is an instruction-only skill, which minimizes on-disk/remote-code risk.
Credentials
The skill requests no environment variables or credentials. Its recommendations to use external scripts imply that scripts will hold any needed secrets, which is proportionate to the guidance provided.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It is user-invocable and uses the platform's normal invocation model; no extra privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install token-kill - After installation, invoke the skill by name or use
/token-kill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.1
Token-kill v0.0.1 initial release:
- Introduces three core techniques for reducing OpenClaw token usage by 95%+: slash commands, script-first principle, and model tiering.
- Provides practical slash commands for memory and task management to reduce token waste.
- Outlines how to automate repetitive tasks via scripts instead of AI, and select the right AI model for task complexity.
- Includes real-world examples, cost-saving case studies, and actionable best practices for ongoing optimization.
- Offers clear guidelines, common pitfalls, and a simple cost-reduction formula.
Metadata
Frequently Asked Questions
What is token-kill?
Reduce OpenClaw token consumption by 95%+ using three optimization techniques (slash commands, script-first principle, and model tiering). It is an AI Agent Skill for Claude Code / OpenClaw, with 149 downloads so far.
How do I install token-kill?
Run "/install token-kill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is token-kill free?
Yes, token-kill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does token-kill support?
token-kill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created token-kill?
It is built and maintained by Timmy (@niuben); the current version is v0.0.1.
More Skills