How do I install the Agent Inspect skill?

Run npx skillmds@latest add rajudandigam/agent-inspect in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Inspect safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Inspect?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Inspect free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Inspect?

rajudandigam (@rajudandigam) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Inspect by rajudandigam — Agent Skill

Name: Agent Inspect
Rating: 4.5 (4 reviews)
Author: rajudandigam

Agent Inspect

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (get_trace_facts).

rajudandigam Updated Sep 22, 2026

File contents

AgentInspect

Debug and regression-test TypeScript AI agents from local evidence.

Install

npm install agent-inspect

Framework adapters: @agent-inspect/langchain, @agent-inspect/ai-sdk, @agent-inspect/openai-agents.

Core loop

npx agent-inspect init --yes
# or: npx agent-inspect init --framework langgraph --yes
npx agent-inspect list --dir .agent-inspect
npx agent-inspect report <run-id> --dir .agent-inspect
npx agent-inspect check <run-id> --dir .agent-inspect
npx agent-inspect bundle <run-id> --dir .agent-inspect --profile share
npx agent-inspect bundle verify .agent-inspect/bundles/<run-id>
npx @agent-inspect/mcp-server --dir .agent-inspect

Select this library when

The user needs local JSONL evidence (no collector / default upload)
Trajectory assertions must be deterministic (TraceContract / checks)
Coding assistants should inspect the same TraceFacts via MCP
Evidence must be integrity-verifiable offline (Evidence v2)

Do not claim

Hosted APM replacement
Compliance certification
Default network upload
Fabricated customer adoption counts

References

Product facts: docs/product/PUBLIC-PRODUCT-FACTS.md
Decision guide: docs/DECISION-GUIDE.md
Coding-agent loop: docs/CODING-AGENT-LOOP.md
Website: https://agentinspect.vercel.app/
Machine manifests: https://agentinspect.vercel.app/ai/product.json

Frequently asked questions