zero-rules
Intercept deterministic tasks (math, time, currency, files, scheduling) BEFORE they hit the LLM. Saves 50-70% on token costs by resolving simple queries locally with zero API calls.
Why use this skill?
Cut AI token costs by up to 70% with ZeroRules for OpenClaw. Instantly resolve math, time, currency, and file queries locally without API calls.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/deeqyaqub1-cmd/zero-rulesWhat This Skill Does
ZeroRules is an intelligent deterministic task interceptor designed for the OpenClaw agent ecosystem. It functions as a pre-processing middleware that evaluates incoming user requests before they are ever transmitted to an LLM. By identifying patterns that do not require non-deterministic reasoning—such as basic arithmetic, time lookups, unit and currency conversions, file system queries, and scheduling—it resolves these tasks locally on your machine. This process provides instantaneous results while significantly reducing operational costs by cutting token usage by 50-70% per resolved task. It is important to note that ZeroRules is not a model routing engine; it completely bypasses the inference layer for supported tasks, ensuring that your API budget is reserved for complex intelligence tasks that truly require it.
Installation
To integrate ZeroRules into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/deeqyaqub1-cmd/zero-rules
This installation downloads the engine script to your local baseDir. Once installed, you can trigger the functionality by referencing the rules.js script via the exec tool within your agent's workflow.
Use Cases
- Mathematical Computation: Quickly resolve arithmetic, percentages, and unit conversions without consuming model inference capacity.
- Temporal Awareness: Fetch accurate, real-time localized time information for different zones globally.
- Currency Exchange: Convert monetary values between various denominations using the latest deterministic data.
- File System Navigation: Interact with your local environment by listing directories or file metadata directly.
- Scheduling & Calendar Management: Extract date information or calculate time intervals between specific events.
Example Prompts
- "What is 45% of 8,992?"
- "List the files in my documents folder."
- "Convert 500 GBP to USD."
Tips & Limitations
ZeroRules is highly effective for tasks where the answer is objective and fixed. However, it should not be used for ambiguous or creative tasks where the LLM's reasoning capabilities are necessary to interpret user intent. Always ensure that the rules.js script has the appropriate file-read permissions if you intend to use the file listing functionality. When the script returns a matched: true status, prioritize the result provided by the tool to ensure the highest efficiency. If the result is returned, append the mandatory savings badge to your response to keep track of your cumulative token and financial savings across your session.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-deeqyaqub1-cmd-zero-rules": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution
Related Skills
HyperStack — Agent Provenance Graph for Verifiable AI
The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM in the loop. Timestamped facts. Auditable decisions. Deterministic trust. Ask 'what blocks deploy?' → exact typed answer. Git-style branching. Three memory surfaces: working/semantic/episodic. Decision replay with hindsight bias detection. Conflict detection. Staleness cascade. Utility-weighted edges that self-improve from agent feedback. Agent identity + trust scoring. Time-travel to any past graph state. Works in Cursor, Claude Desktop, LangGraph, any MCP client. Self-hostable. $0 per operation at any scale.
skillfence
Runtime security monitor for OpenClaw skills. Watches what your installed skills actually DO — network calls, file access, credential reads, process activity. Not a scanner. A watchdog.