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.
npx skills add jschuller/mcp-server-servicenow --skill reviewing-sla-definitionsgit clone --depth 1 https://github.com/jschuller/mcp-server-servicenowWrote 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.
[](https://agentmods.dev/skills/jschuller/mcp-server-servicenow/reviewing-sla-definitions)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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_slameans 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_slameans breach rates are not assessable with this identity. aggregate_recordsrefused (401 under API-key auth, or 403): count fromlist_recordsrows 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
- Read the definitions, with no query:
Page withlist_records(table_name="contract_sla", fields="sys_id,name,collection,type,target,duration,schedule,start_condition,stop_condition,pause_condition,active", limit=500)offsetuntil a page comes back empty. - Group the active definitions by
collection,targetandtype. 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.
- Breach counts per definition. Try the aggregate first:
If it is refused, read the rows and count them yourself:aggregate_records(table_name="task_sla", group_by="sla,has_breached")
Page until empty. A definition's breach rate is breached rows over all rows that are notlist_records(table_name="task_sla", fields="sla,sla.name,has_breached,stage", limit=500)cancelled. - Definitions with no
task_slarows at all never attach. Their start condition may be impossible, or the process changed. - 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.
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.
- 2d ago First seen · 75 lines · 79 tokens per session scan A 48ac3972d6a4
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.
Other skills, from other repositories
cor-api-tools
Deep reference for all 61 COR MCP API tools — complete argument listings, JSON request/response examples, and common usage patterns for every module.
cor-mcp-server
Main skill for the COR MCP Server — a comprehensive MCP server that exposes 61 Project COR API tools via FastMCP with dual auth (email/password or client credentials), stdio/SSE transport, and auto-refreshing OAuth 2.0.
cor-mcp-setup
Set up and use the COR MCP Server — 61 tools for Project COR (projects, tasks, clients, time tracking, teams). Covers both auth modes: email/password and API key + client secret.
report-issue
File a bug or feature request against this repository (cyanheads/git-mcp-server) using the gh CLI. Use for tool logic bugs, git provider misbehavior, transport issues, auth/config problems, or new feature proposals.
papi-plan
Invoke when starting a new PAPI cycle. Covers plan generation, board management, and cycle scoping rules.
papi-idea
Invoke when submitting backlog ideas, registering docs, or filing research. Covers idea pipeline and doc registry conventions.