by epsilla-cloud · Codex Skill · ★ 45
Cost-aware tracing & skill distillation for LLM agents Website · Docs · Paper · Ask Tracy · Quickstart Paper ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation — Boqin Yuan, Renchu Song, Yue Su, Sen Yang, Jing Qin · arXiv 2604.23853 Skill-distillation pipelines learn reusable rules from LLM agent trajectories, but they lack a key signal — how much each step costs. ClawTrace records every LLM call, tool use,
| Stars | 45 |
| Forks | 9 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 64.7607741040364/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-15 |
| Created | 2026-04-10 |
| Platforms | claude-code, node |
| Est. Tokens | ~12003k |
Explore other popular codex skill tools:
clawtrace is Make your OpenClaw agents better, cheaper, and faster.. It is categorized as a Codex Skill with 45 GitHub stars.
clawtrace is primarily written in TypeScript. It covers topics such as agent-observability, agent-telemetry, ai-agent.
You can find installation instructions and usage details in the clawtrace GitHub repository at github.com/epsilla-cloud/clawtrace. The project has 45 stars and 9 forks, indicating an active community.
clawtrace is released under the Apache-2.0 license, making it free to use and modify according to the license terms.