by luoyuctl · Codex Skill · ★ 55
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
AgentTrace Local-first TUI and reports for AI coding-agent session history, cost, tokens, time, and slow-run diagnosis. English | 简体中文 <img src="assets/readme-real-run.gif" alt="agenttrace run
| Stars | 55 |
| Forks | 2 |
| Language | Go |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 38.2/100 |
| Open Issues | 9 |
| Last Updated | 2026-06-07 |
| Created | 2026-05-01 |
| Platforms | claude-code, cli, codex, gemini, go |
| Est. Tokens | ~1839k |
Looking for a agenttrace alternative? If you're comparing agenttrace 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.
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" tha
Agent skills for Spec Kit
AI Coding stats dashboard — track costs, tokens, and efficiency across Claude Code / Gemini CLI / Codex / Curs
Process manager for AI agents (and humans)
Unified Emacs interface supporting OpenAI Codex, GitHub Copilot CLI, Claude Code, Gemini CLI, Opencode, and mo
Explore other popular codex skill tools:
agenttrace is Local-first TUI for AI coding-agent session history: trace cost, tokens, time, tool failures, latency, health, diffs, reports, and CI gates across local agent logs.. It is categorized as a Codex Skill with 55 GitHub stars.
agenttrace is primarily written in Go. It covers topics such as agent-session-replay, ai-agent-observability, ai-agents.
You can find installation instructions and usage details in the agenttrace GitHub repository at github.com/luoyuctl/agenttrace. The project has 55 stars and 2 forks, indicating an active community.
agenttrace is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agenttrace on Agent Skills Hub include toktrack, terminal-jarvis, speckit-agent-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.