by jinzijian · Codex Skill · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.
| Stars | 84 |
| Forks | 2 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 50.3531342510438/100 |
| Last Updated | 2026-08-21 |
| Created | 2026-08-19 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~13k |
These tools work well together with EvoTrace for enhanced workflows:
Looking for a EvoTrace alternative? If you're comparing EvoTrace with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Lightweight agent orchestration dev tool that lives in your repo
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with sem
Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and mu
Find that one coding agent session you want to get back to!
Agent skills for Spec Kit
An LLM council that reviews your coding agent's every move
Explore other popular codex skill tools:
EvoTrace is Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.. It is categorized as a Codex Skill with 84 GitHub stars.
EvoTrace is primarily written in Python. It covers topics such as agents, benchmark, claude-code.
You can find installation instructions and usage details in the EvoTrace GitHub repository at github.com/jinzijian/EvoTrace. The project has 84 stars and 2 forks, indicating an active community.
EvoTrace is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to EvoTrace on Agent Skills Hub include sudocode, grace-marketplace, aiwg. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: