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 analyzing-accessgit 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/analyzing-access)<a href="https://agentmods.dev/skills/jschuller/mcp-server-servicenow/analyzing-access"><img src="https://agentmods.dev/badge/skills/jschuller/mcp-server-servicenow/analyzing-access/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/analyzing-access"><img src="https://agentmods.dev/badge/skills/jschuller/mcp-server-servicenow/analyzing-access.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 | $0.00151 | $0.02615 |
| Opus 5.5 | $0.00060 | $0.01046 |
| Sonnet 5.5 | $0.00030 | $0.00523 |
| Haiku 4.5 | $0.00015 | $0.00262 |
Grade A, and why
analyzing-access 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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing ServiceNow Access
Two jobs: review role and group hygiene across users, and explain why a call was denied or came back incomplete. Everything here is read-only. See references/access-errors.md for the denial messages and what each one means, and references/acl-evaluation.md for how ServiceNow decides access.
Tables and roles
| Table | What it answers | Readable with |
|---|---|---|
sys_user_has_role |
Which user holds which role, directly or inherited | itil (all users' rows); snc_read_only alone gets 403 |
sys_user_grmember |
Group membership; group names come from sys_user_group through group.name |
itil |
sys_group_has_role |
Which roles a group grants | itil |
sys_user |
active, last_login_time |
snc_read_only |
sys_security_acl |
The ACL rules themselves | admin / security_admin only: 403 for least-privilege identities |
Role names come through dot-walks (role.name). The role table itself (sys_user_role) usually hides some or all of its rows from least-privilege identities, so role.name can come back empty (observed for admin and security_admin) while a filter on role.name=admin still matches. Workflow 5 covers dot-walks and their limits.
When access is denied
- 403 on a table: not assessable with this identity. Say so, name the table, and move on; don't guess.
- 0 rows or fields missing from every row (
list_recordsadds awarning): possibly hidden by an ACL, not proof that nothing exists. - 401 under API-key auth on aggregates or single-record reads: a REST API access policy doesn't cover that API; table reads still work.
Workflows
1. Who holds privileged roles
Progress checklist:
- [ ] List active admin and security_admin grants
- [ ] Flag inactive users and stale logins among them
- [ ] Separate direct grants from group grants
- [ ] Report counts and the accounts to review
- List the grants, with enough user context to judge each one:
Iflist_records(table_name="sys_user_has_role", query="role.nameINadmin,security_admin^state=active", fields="user.user_name,user.active,user.last_login_time,role,role.name,inherited", limit=200)role.namecomes back empty, tell the two roles apart by therolesys_id, or run the query once per role. - A row with
inherited=falseis a direct grant. An inherited row came through a group or through a role that contains this one. To find the group, intersect the user's groups with the groups that grant the role (workflow 2, step 3):list_records(table_name="sys_user_grmember", query="user.user_name=<user>", fields="group.name", limit=100)granted_bystill names the group on some instances, but ServiceNow has deprecated it, so don't rely on it. - Report the holder count per role, then the accounts to review first: inactive users, users with no recent login, and direct grants.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +33 lines · +36 tokens per session 9e2a9e03161c
- 9d ago First seen · 108 lines · 115 tokens per session scan A 4bf2554e7b73
analyzing-access is a skill published in the GitHub repository jschuller/mcp-server-servicenow (25 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 2,615 once invoked, about $0.0006 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
swag
This skill should be used when the user says "add proxy config", "create reverse proxy", "SWAG config", "nginx proxy", "expose service", "proxy configuration", "subdomain config", "subfolder config", "configure SWAG", "list proxy configs", "view proxy config", "edit proxy config", "remove proxy config", "check proxy…
scholar-workflow
Use when the user asks you to search, retrieve, or reason about scholarly sources — papers, patents, books, or standards — guides tool selection, chaining, and cross-domain workflows.
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-auth
Authentication cheat sheet for the COR MCP Server — covers both auth modes (email/password and client credentials) step by step, token refresh mechanism, and common auth errors.
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.