Skill Detail
Inspect agent model traffic with LLMTrace
Proxy OpenAI-compatible model traffic so operators can inspect prompts, detect risks, and enforce budget or policy controls.
Security & VerificationMulti-Framework
Security & Verification
Multi-Framework
Security Reviewed
⭐ 46 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill inspect-agent-model-traffic-with-llmtrace
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Rust or Docker runtime, OpenAI-compatible client or SDK
Install & setup
Install with
curl -sS https://raw.githubusercontent.com/epappas/llmtrace/main/scripts/install.sh | bash or cargo install llmtrace, run llmtrace-proxy --config config.yaml, then point your OpenAI-compatible client at the local proxy base URL.Author
epappas
Publisher
Individual
Last updated
Apr 17, 2026
Quick brief
Use LLMTrace when an operator wants to put OpenAI-compatible traffic behind a proxy that can inspect prompts, flag prompt injection or PII, and enforce cost or policy controls before responses hit downstream systems. Invoke it instead of calling the model endpoint directly when the task is security and observability around agent traffic, not routine application usage. The boundary is a traffic-inspection and guardrail workflow for model calls, not a generic SDK, model host, or broad observability platform listing.