agent-inspect

Name: agent-inspect
Author: rajudandigam

Issues

Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..

208stars

88forks

TypeScript

Installation

# Add to your Claude Code skills
git clone https://github.com/rajudandigam/agent-inspect

Getting Started

Guides for using ai agents skills like agent-inspect.

Security ReportIssues

Last scanned: 7/2/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "@vitest/coverage-v8: Vulnerability found",
      "severity": "critical"
    },
    {
      "type": "npm-audit",
      "message": "@vitest/mocker: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "vite-node: Vulnerability found",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "vitest: Vulnerability found",
      "severity": "critical"
    }
  ],
  "status": "FAILED",
  "scannedAt": "2026-07-02T07:32:21.144Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is agent-inspect?

agent-inspect is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by rajudandigam. Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers. It has 208 GitHub stars.

Is agent-inspect safe to use?

agent-inspect failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.

How do I install agent-inspect?

Clone the repository with "git clone https://github.com/rajudandigam/agent-inspect" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is agent-inspect written in?

agent-inspect is primarily written in TypeScript. It is open-source under rajudandigam on GitHub, so you can review or fork the full source.

Are there alternatives to agent-inspect?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-inspect against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

medical-research-skills brain.md

agent-inspect turns AI-agent runs into readable local execution trees: framework events, observed objects, tool calls, LLM steps, retries, failures, timings, sessions, and CI artifacts — without an account, collector, or hosted dashboard.

Default loop: capture locally → inspect / report / diff → check in CI → redact before sharing.

npm install agent-inspect

60-second quickstart

npx agent-inspect init --yes
node examples/agent-inspect-demo.mjs
npx agent-inspect list --dir .agent-inspect
npx agent-inspect view <run-id> --dir .agent-inspect
npx agent-inspect report <run-id> --dir .agent-inspect
npx agent-inspect verify-safe --dir .agent-inspect

Install → one trace → one failure check → one share-safe artifact in under five minutes. Guide: First trace in 5 minutes · repo

Choose your path

Path	Use when	Start
AI SDK	Vercel AI SDK `generateText` / `streamText`	`@agent-inspect/ai-sdk` · guide
OpenAI Agents	OpenAI Agents JS	`@agent-inspect/openai-agents` · guide
LangChain	Callbacks / LangGraph-via-LangChain	`@agent-inspect/langchain`
Observe	Object/class with `run` / `execute` / `invoke`	Getting started
Manual	Custom spans and nesting	`inspectRun` + `step` in API
Logs	Structured logs already emitted	Log-to-tree
CI / tests	Failed-test artifacts	`@agent-inspect/vitest` · `@agent-inspect/jest`
Real projects	Fixture runner / bootstrap	`@agent-inspect/harness` · NestJS

Blessed starters (no API keys): examples/starters

What it helps with

Wrong tool call — tool steps, args metadata, and parent run in one tree
Failed eval / test — check, eval, Vitest/Jest reporters on failure
Baseline vs candidate — local diff of two runs
PR trace artifact — CI artifacts + redact --profile share
Safe incident handoff — safe sharing before Slack or GitHub
Multi-agent / sessions — sessions, search, handoff metadata
MCP tool calls — @agent-inspect/mcp client tracing
VS Code review — in-repo extension (dev guide; Marketplace not published yet)
Existing logs — parse structured logs when you cannot instrument

Real-world scenarios

Scenario	Where to start
Local debugging	Use cases · broken-agent starter
CI failure review	CI artifacts · ci-eval-redact
Team adoption	Team workflows · Design partners
Safe sharing	Safe sharing · repo
Framework-native tracing	Adapters · package READMEs above
Design partner trial	Design partner guide · Demo script

Package map

Package	Purpose
`agent-inspect`	Core APIs + CLI
`@agent-inspect/ai-sdk`	AI SDK telemetry
`@agent-inspect/openai-agents`	OpenAI Agents processor
`@agent-inspect/langchain`	LangChain callbacks
`@agent-inspect/harness`	Fixture runner for real projects
`@agent-inspect/redact`	Deterministic redaction
`@agent-inspect/eval`	Local eval heuristics
`@agent-inspect/vitest`	Vitest reporter
`@agent-inspect/jest`	Jest reporter
`@agent-inspect/mcp`	MCP client tracing
`@agent-inspect/mcp-server`	Read-only trace MCP server
`@agent-inspect/guardrails`	Deterministic guardrail rules
`@agent-inspect/circuit`	Loop / retry / timeout analyzers
`@agent-inspect/viewer`	Localhost viewer
`@agent-inspect/adapter-sdk`	Third-party adapters
`@agent-inspect/tui`	Optional terminal UI
`agent-inspect-vscode`	VS Code extension (in-repo; not on Marketplace yet)

Safety model

Traces are local JSONL under .agent-inspect/ (or AGENT_INSPECT_TRACE_DIR)
Metadata-only by default — no raw prompts/outputs unless you opt in
No hidden upload — AgentInspect does not send traces to the cloud
Redaction profiles — local / share / strict via CLI or @agent-inspect/redact
scan / verify-safe — check artifacts before sharing
Not a chain-of-thought recorder or compliance engine — review exports before posting

Details: Safe sharing · repo · Security

Documentation

	Website	Repo
Getting started	docs/getting-started	GETTING-STARTED.md
Safe sharing	docs/safe-sharing	SAFE-TRACE-SHARING.md
Compare	docs/compare	COMPARE.md
API / CLI	—	API.md · CLI.md
Adoption	—	ADOPTION.md · USE-CASES.md
Technical guide	—	TECHNICAL-GUIDE.md
Examples	—	starters
Visual demos	—	SCREENSHOTS.md

Full index: docs/README.md

What AgentInspect is not

Hosted SaaS or dashboard product
Production APM replacement (use LangSmith, Langfuse, OTel, etc. alongside)
Eval dataset platform or LLM-as-judge service
Prompt registry or provider pricing engine
Default telemetry uploader or replay engine

See Compare.

Install details

Current release: 3.5.5 (sixteen linked npm packages). Persisted trace schema 1.0. Requires Node.js >= 20.

pnpm add agent-inspect
npx agent-inspect doctor

Monorepo development: pnpm install && pnpm build && pnpm test

Contributing

CONTRIBUTING.md · Good first issues · Discussions · Changelog

Redact traces before posting issues or PRs.