# Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems

DevFeed: [Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems](<https://devfeed.tech/articles/don-t-prompt-your-agents-equip-them-skillware-as-a-modular-standard-for-sovereign-auditable-and-deterministic-capability-execution-for-logical-systems-120227.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07652>)

Author: Vladimiros Peilivanidis (ARPA Hellenic Logical Systems)

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [adapters](<https://devfeed.tech/tags/adapters.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-reliability](<https://devfeed.tech/tags/agent-reliability.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automated](<https://devfeed.tech/tags/automated.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-apis](<https://devfeed.tech/tags/cloud-apis.md>), [code](<https://devfeed.tech/tags/code.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [execution](<https://devfeed.tech/tags/execution.md>), [logical](<https://devfeed.tech/tags/logical.md>), [modular](<https://devfeed.tech/tags/modular.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [standard](<https://devfeed.tech/tags/standard.md>), [systems](<https://devfeed.tech/tags/systems.md>)

## AI overview

Skillware packages agent capabilities as modular, versioned bundles containing typed JSON inputs, deterministic Python code, task directives, datasets, and unit tests. In-process adapters expose these capabilities as native tools to cloud and local models. Across 368 benchmark conditions, the authors report that equipped local models with 3B-8B parameters outperformed unequipped frontier models on complex multi-step workflows, with up to 84.8% fewer tokens, 97.3% lower inference costs, and no parameter errors. These are reported evaluation results; the supplied text does not describe the benchmarks in detail. The framework is proposed as a basis for auditable, real-time capability execution, with potential extension to IoT, drones, and robotics.

## Source excerpt

arXiv:2611.07652v1 Announce Type: new Abstract: Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt engineering. In practice, this burns massive context windows, inflates API bills, and produces brittle agents that fail unpredictably in production. In this work, we present Skillware, an open architectural framework and capability registry that formally separates what an agent wants to do from how that task is executed. Instead of prompting models with loose text instructions or markdown files baptized as 'skills', Skillware equips them with modular, versioned software capability bundles. Much like skill hotkeys in video games that execute deterministically under fixed world rules, each bundle combines a typed JSON input contract, deterministic Python code, task directives, bundled datasets, and automated unit tests. In-process adapters translate these capabilities into native tool declarations for any model, from frontier cloud APIs to local open-weight runtimes with zero network latency. Evaluating 23 frontier and open-weight models across 368 benchmark conditions, we show that small local models (3B to 8B parameters) equipped with Skillware consistently outperform unequipped frontier models on complex multi-step workflows. They cut token usage by up to 84.8%, slash inference costs by up to 97.3%, and eliminate parameter errors entirely. True agent reliability does not come from larger models or longer prompts, but from equipping logical systems with verified, deterministic software. Finally, we articulate the trajectory of capability bundles across an invariant continuum of information processing systems: from digital logical systems today, to IoT, drones, and embodied robotics tomorrow, establishing a foundation for auditable, real-time capability execution.