trace-multi-agent-system
100 / 100 · Low risk
Fine to try.
Use this to add observability to a multi-agent or agentic system (multiple agents, sub-agents, tool loops, handoffs). Trigger on "trace my agents", "my agent crew is a black box", "which agent failed", "debug my LangGraph/CrewAI/AutoGen/agent workflow", "the agents loop forever". Get a clear span tree across agents and tool calls so you can see who did what.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'trace-multi-agent-system' ] || [ -L ~/.agents/skills/'trace-multi-agent-system' ]; then echo 'A skill folder named trace-multi-agent-system already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ContextJet-ai/awesome-llm-observability' "$d" && git -C "$d" checkout --quiet '5c10e286ca717b1dd556df7242957fee1efd9d4a' -- 'skills/trace-multi-agent-system' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/trace-multi-agent-system' ~/.agents/skills/'trace-multi-agent-system' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'trace-multi-agent-system' ~/.claude/skills/'trace-multi-agent-system' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/ContextJet-ai/awesome-llm-observability/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 5c10e28 | 100 |
| 2026-11-09 | c2ff5d5 | 100 |
| 2026-11-07 | 1516bb1 | 100 |