# AgentWatch

> Use this tool when you need to monitor and analyze event streams from various AI agents, such as Claude Code, Codex, and Gemini CLI, to identify anomalies, track costs, and optimize performance. AgentWatch provides a unified timeline, token accounting, and hybrid search capabilities, allowing for efficient troubleshooting and debugging. It is ideal for developers and researchers working with multiple AI agents, offering a comprehensive interface for real-time monitoring and optimization.

Canonical page: https://skillsregistry.net/skills/mishanefedov-agentwatch  
JSON: https://api.skillsregistry.net/v1/skills/mishanefedov-agentwatch

## Description

A terminal live-tail and a browser dashboard — one process, one event stream, served from localhost. Unified timeline across Claude Code, Codex, Gemini CLI, Cursor, Hermes, and OpenClaw. Token + cost accounting, compaction + anomaly detection, hybrid search, SVG call graphs, monaco-style diff attribution, agent-aware replay ("what would the agent say if I edited the prompt?"), policy editor, MCP s

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-05-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a3msd83c8j)
- **Repository:** <https://github.com/mishanefedov/agentwatch>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mishanefedov-agentwatch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mishanefedov-agentwatch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mishanefedov-agentwatch/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt