Sn Investigator — Development agent for Claude Code
Read-only ServiceNow investigator.
How to install Sn Investigator
Installs to ~/.claude/agents/ivanbbaev-servicenow-mcp-ai-sn-investigator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/IvanBBaev/servicenow-mcp-ai/HEAD/agents/sn-investigator.md -o ~/.claude/agents/ivanbbaev-servicenow-mcp-ai-sn-investigator.md Restart Claude Code, or start a new session, for it to be picked up.
What Sn Investigator does
name: sn-investigator description: Read-only ServiceNow investigator. Use proactively to answer a question about a ServiceNow instance — why a record looks the way it does, what automation runs on a table, where a field or script is used, why a flow failed — without filling the main conversation with raw records. Returns a short report with its evidence. tools: mcp__plugin_servicenow-mcp-ai_servicenow__servicenow_get_status, mcp__plugin_servicenow-mcp-ai_servicenow__servicenow_list_instances
Alternatives in Development
- ClawPort -- Setup Guide — This guide walks you through getting ClawPort running against your own OpenClaw instance 648 ★
- Claude Bowser Agent — Browser automation agent 222 ★
- Openclaw Debugger — Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift 75 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Log Format Auditor
Scans real Claude Code logs (~/.claude/projects) read-only and reports drift from Kairos's interpretation rule
Structurer
Turns a user's free-text answer into a decision record in the schema. Use immediately after the user answers a
Site Guide
Use this agent for any question about the AZM X website that is answered from its documentation and record: ho
Sn Change Reviewer
Read-only reviewer for a planned ServiceNow change. Use before applying a write — pass it the plan preview the
Git Archaeologist
Explains why code is the way it is by tracing it through git history, blame, pickaxe searches, and linked PRs.
Scaffold
Mechanical, low-judgment file work — boilerplate files, config stubs, repetitive edits across many files, rena
Related Skills
Servicenow Claude MCP
Connecting Claude to a production ServiceNow instance: per-user OAuth through the ServiceNow SDK, guarded read
Push Back
Verify a claim against code+docs+memory before acting. Run when a finding/audit/recommendation looks suspect,
Modes
When updating your task boundary, you must explicitly set your current agent mode. Think of this as a way of f
