maple-agent-tracing
Trace an AI agent or LLM app with Maple so each conversation shows up as one Agent Session with its transcript, model calls, tool calls, tokens, cost and failures. Detects the agent framework (Vercel AI SDK, eve, OpenAI Agents SDK, Mastra, LangChain/LangGraph, Claude Agent SDK, Pydantic AI, LlamaIndex, CrewAI, Google ADK, Strands, smolagents, Agno, DSPy, Haystack, Microsoft Agent Framework, Spring AI, LiteLLM, OpenRouter, raw provider SDKs) and installs the matching per-framework skill. Triggers on 'trace my agent', 'add agent observability', 'LLM tracing with Maple', 'set up Maple agent sessions', 'OpenTelemetry for my AI agent'.
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs downloading and executing remote agent skills from GitHub via `npx skills` or direct raw URLs referencing MapleTechLabs/maple, representing an unverified third-party operational dependency.
- Repository
MapleTechLabs/maple
- Revision
f7394ac
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.