triage

triage is a command for Claude Code from jschuller/mcp-server-servicenow. It costs 22 tokens per session (556 once invoked), scanned A, original, MIT.

A command for handling ServiceNow incidents, which are records of problems affecting an organisation’s IT services. It can route requests for listing, investigating, prioritising, or analysing incidents.

In plain words
What is it for?
Use it to list recent incidents, focus on P1 or P2 incidents, investigate a specific incident number, assess a new incident, or analyse incident trends and service-level targets.
Why use it?
It structures incident work so open and urgent problems can be found, investigated, and assessed consistently.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the servicenow plugin — 4 skills, 4 commands, 1 agent, 1 MCP server shipped together

Good fit Use it to list recent incidents, focus on P1 or P2 incidents, investigate a specific incident number, assess a new incident, or analyse incident trends and service-level targets.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jschuller/mcp-server-servicenow/triage
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/jschuller/mcp-server-servicenow

Made for: Claude Code.

Or install servicenow, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 1 agent, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/jschuller/mcp-server-servicenow/triage.svg)](https://agentmods.dev/commands/jschuller/mcp-server-servicenow/triage)
Your own site
<a href="https://agentmods.dev/commands/jschuller/mcp-server-servicenow/triage"><img src="https://agentmods.dev/badge/commands/jschuller/mcp-server-servicenow/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 556 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00556
Opus 5 $0.00011 $0.00278
Sonnet 5 $0.00004 $0.00111
Haiku 4.5 $0.00002 $0.00056

Measured 8d ago against content hash 9b2f17ac34e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/triage.md · 39 lines

What it actually says

/servicenow:triage

Route based on $ARGUMENTS:

No arguments or general request

If $ARGUMENTS is empty, contains "what's on fire", "open", "recent", or "list":

  • Run the List Recent Incidents workflow from the triaging-incidents skill.
  • Show open incidents sorted by priority, highlight any P1/P2.

Specific INC number

If $ARGUMENTS contains an INC number (e.g., "INC0010001"):

  1. Find the incident: list_records(table_name="incident", query="number=$ARGUMENTS", limit=1)
  2. Run the Investigate an Incident workflow — get full details, check CI dependencies, find similar incidents, check related problems/changes.
  3. Present findings with recommended actions.

Priority filter

If $ARGUMENTS contains "P1", "P2", "critical", or "high priority":

  • Filter incidents by the specified priority level.
  • Run the List Recent Incidents workflow with the appropriate priority filter.

Triage request

If $ARGUMENTS contains "triage", "assess", or "new":

  • Run the Triage a New Incident workflow — assess impact/urgency, check CI blast radius, suggest priority and assignment.

Trend analysis

If $ARGUMENTS contains "trends", "analysis", "bulk", or "SLA":

  • Run the Bulk Analysis workflow — top categories, repeat CIs, SLA breaches.

Fallback

For any other input, treat $ARGUMENTS as a search term:

  • list_records(table_name="incident", query="short_descriptionLIKE$ARGUMENTS^active=true", limit=10)
  • Present matching incidents and offer to investigate any of them.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 39 lines · 22 tokens per session scan A 9b2f17ac34e4

Subscribe to this mod's changes

triage is a command published in the GitHub repository jschuller/mcp-server-servicenow (17 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 556 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.