Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
Summary
The LOOP Skill Engine achieves 99% success and 99% token reduction for periodic AI agent tasks by recording a single LLM-driven execution and replaying it deterministically via a parameterized, branch-free skill, eliminating stochastic failures and high costs.
View Cached Full Text
Cached at: 05/15/26, 06:22 AM
# Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay Source: [https://arxiv.org/abs/2605.14237](https://arxiv.org/abs/2605.14237) [View PDF](https://arxiv.org/pdf/2605.14237) > Abstract:Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models \(LLMs\) offer unmatched flexibility in tool orchestration, yet their inherent stochasticity causes unpredictable failures, and repeated invocations incur prohibitive token costs\. We present the LOOP SKILL ENGINE, a system that achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one\-shot recording, deterministic replay paradigm\. On its first run, the agent executes the task with full LLM reasoning while the system transparently intercepts and records the complete tool\-call trajectory\. A greedy length\-descending template extraction algorithm then converts this recording into a parameterized, branch\-free Loop Skill \-\- a deterministic execution plan that captures the task's functional intent while parameterizing time\-dependent and result\-dependent variables\. All subsequent executions bypass the LLM entirely: the engine resolves template variables against real\-time values and replays the tool sequence deterministically\. We prove two theorems: \(1\) Replay Determinism \-\- the step sequence of a validated Loop Skill is invariant across all future executions; \(2\) Write Safety \-\- concurrent access to persistent configuration is serialized through reentrant locks and atomic file replacement\. Across a benchmark of periodic agent tasks spanning intervals from 5 minutes to 24 hours, the Loop Skill Engine reduces monthly token consumption by 93\.3%\-\-99\.98% and cuts execution latency by 8\.7x while eliminating output non\-determinism\. A multi\-layer degradation strategy guarantees that tasks never stall\. We release the engine as part of the buddyMe open\-source agent framework\. ## Submission history From: Xiaohua Wang \[[view email](https://arxiv.org/show-email/fe323865/2605.14237)\] **\[v1\]**Thu, 14 May 2026 01:05:35 UTC \(329 KB\)
Similar Articles
Turn repeated instructions into reusable skills in Lovable (14 minute read)
Lovable introduces Skills, a feature enabling users to create reusable markdown-based instructions and context for AI agents, allowing task-specific playbooks to be applied without repeating instructions.
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
SkillFlow proposes a flow-driven recursive skill evolution framework for LLM-based agentic orchestration, using Tempered Trajectory Balance to prevent strategy collapse and provide transparent credit assignment. Experiments on 14 datasets show significant improvements over baselines in QA, math, code, and decision-making tasks.
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
This paper introduces Formal Skill, a runtime-native abstraction for LLM agents that encodes reusable procedures as executable state machines with JSON metadata, Python executors, and hook-governed control logic. An open-source implementation called FairyClaw is presented, showing competitive performance on Harness-Bench with reduced token usage.
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
SkillFlow introduces a benchmark of 166 tasks across 20 families for evaluating autonomous agents' ability to discover, repair, and maintain skills over time through a lifelong learning protocol. Experiments reveal a substantial capability gap among leading models, with Claude Opus 4.6 improving significantly while others show limited or negative gains from skill evolution.