reviewing-sla-definitions

reviewing-sla-definitions is a skill for Claude Code from jschuller/mcp-server-servicenow. It costs 79 tokens per session (1,097 once invoked), scanned A, original, MIT.

A read-only review tool for ServiceNow service-level definitions, including SLAs, OLAs, and underpinning contracts. It compares the definitions with the task records attached to them.

In plain words
What is it for?
Use it to review breach rates, find conflicting definitions, and identify definitions that are not running.
Why use it?
It shows which definitions breach their targets, overlap, duplicate one another, or never attach, without changing ServiceNow data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the servicenow-change-impact plugin — 2 skills shipped together

Good fit Use it to review breach rates, find conflicting definitions, and identify definitions that are not running.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions
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.

Any agent
npx skills add jschuller/mcp-server-servicenow --skill reviewing-sla-definitions
Clone the repo
git clone --depth 1 https://github.com/jschuller/mcp-server-servicenow

Made for: Claude Code.

Or install servicenow-change-impact, the plugin that ships this one along with the rest of its 2 skills.

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 reviewing-sla-definitions

README.md
[![agentmods](https://agentmods.dev/badge/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions/github.svg)](https://agentmods.dev/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions)
Your own site
<a href="https://agentmods.dev/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions"><img src="https://agentmods.dev/badge/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reviewing-sla-definitions

Your own site · 80×15
<a href="https://agentmods.dev/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions"><img src="https://agentmods.dev/badge/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 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 $0.00079 $0.01097
Opus 5.5 $0.00032 $0.00439
Sonnet 5.5 $0.00016 $0.00219
Haiku 4.5 $0.00008 $0.00110

Measured 2d ago against content hash 48ac3972d6a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewing-sla-definitions 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 2d 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.

examples/change-impact/skills/reviewing-sla-definitions/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing SLA Definitions

Find which SLA definitions breach, which overlap, and which never run. It reads the definitions and the attached task SLAs, and changes nothing.

Tables and roles

Table What it gives Readable with
contract_sla Definitions: name, collection (the task table), type (SLA, OLA, Underpinning contract), target (response or resolution), duration, schedule, start/pause/stop conditions, active itil can read the values, but on a Brazil instance it could filter only on name
task_sla One row per definition attached to a task: sla, task, stage, has_breached, business_percentage itil

When access is denied

  • A 403 "Field(s) present in the query do not have permission to be read" on contract_sla means the identity can read the definitions but not filter on that field. Read them all without a query and group them yourself. There are rarely more than a few hundred.
  • A 403 on task_sla means breach rates are not assessable with this identity.
  • aggregate_records refused (401 under API-key auth, or 403): count from list_records rows instead.

Workflow

Progress checklist:

- [ ] Read every definition
- [ ] Group them by table, target and type; flag overlaps
- [ ] Count attached task SLAs and breaches per definition
- [ ] Flag definitions that never attach
- [ ] Recommend which to merge, retire or review
  1. Read the definitions, with no query:
    list_records(table_name="contract_sla", fields="sys_id,name,collection,type,target,duration,schedule,start_condition,stop_condition,pause_condition,active", limit=500)
    
    Page with offset until a page comes back empty.
  2. Group the active definitions by collection, target and type. Within a group, compare start conditions:
    • Overlap: two definitions whose start conditions can both match the same task. Both attach, and the task is measured twice.
    • Near-duplicates: the same conditions with different durations or schedules. They usually mean one replaced the other without being retired.
  3. Breach counts per definition. Try the aggregate first:
    aggregate_records(table_name="task_sla", group_by="sla,has_breached")
    
    If it is refused, read the rows and count them yourself:
    list_records(table_name="task_sla", fields="sla,sla.name,has_breached,stage", limit=500)
    
    Page until empty. A definition's breach rate is breached rows over all rows that are not cancelled.
  4. Definitions with no task_sla rows at all never attach. Their start condition may be impossible, or the process changed.
  5. Report:
    • the overlapping groups;
    • each definition with its row count and breach rate;
    • the definitions that never attach;
    • recommendations: merge overlaps, retire the unused, and look first at high breach rates on high-priority targets.

Read the full file on GitHub · 75 lines

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. 2d ago First seen · 75 lines · 79 tokens per session scan A 48ac3972d6a4

Subscribe to this mod's changes

reviewing-sla-definitions is a skill published in the GitHub repository jschuller/mcp-server-servicenow (24 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 1,097 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.