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 serac-labs/serac --skill service-portal-pagesgit clone --depth 1 https://github.com/serac-labs/seracWrote 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/serac-labs/serac/service-portal-pages)<a href="https://agentmods.dev/skills/serac-labs/serac/service-portal-pages"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/service-portal-pages/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/serac-labs/serac/service-portal-pages"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/service-portal-pages.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 | $0.00063 | $0.01505 |
| Opus 5.5 | $0.00025 | $0.00602 |
| Sonnet 5.5 | $0.00013 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
service-portal-pages 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Portal Pages and Themes
widget-coherence covers the inside of one widget — server script, client controller and HTML staying in
step. This covers everything around it: the page the widget sits on, and the theme the page renders in.
The hierarchy
sp_portal one portal. Has a URL suffix ("sp"), a homepage, and a THEME.
└── sp_page a page, addressed by its stable `id` → /sp?id=<id>
└── sp_row a row in the page layout
└── sp_column a column in that row (12-column grid)
└── sp_instance ONE PLACEMENT of one widget, with its options
└── sp_widget the widget definition, shared by every instance
The two things to hold onto:
A page is not "in" a portal. sp_page has no portal reference. A page is reachable from any portal
as /<portal-suffix>?id=<page-id>; what ties it to one is being that portal's homepage, or being linked
from a menu. Listing pages "for a portal" is therefore a convenience filter, not a containment query.
id is the address, sys_id is the record. sp_page.id is the human-readable stable key that
appears in the URL. Both are accepted by the management tool; the id is what a user will quote at you.
Creating and placing
await snow_create_sp_page({ id: "team_requests", title: "Team requests", public: false })
await snow_sp_page_manage({ action: "add_widget_instance", id: "team_requests",
widget_id: "widget-my-requests", column_sys_id: colSysId, order: 100 })
public: true means reachable without login — anonymous. It is the one field on this page worth a second
look before setting it.
add_widget_instance prefers column_sys_id. Omitting it attaches the instance to the page directly,
which renders but sits outside the grid; a page built that way cannot be laid out afterwards without
recreating the instances. Build rows and columns first when the layout matters.
Widget options live on the instance
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.
- 1mo ago First seen · 131 lines · 63 tokens per session scan A e059a944cf42
service-portal-pages is a skill published in the GitHub repository serac-labs/serac (77 stars, last pushed 17d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,505 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 2026-09-11.
service-portal-pages compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| service-portal-pagesserac-labs/serac | Skill | 77 | 17d ago | Apache-2.0 | A | 63 | Claude Code |
| sn-safe-writeIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 43 | Claude Code |
| sn-discoverIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 53 | Claude Code |
| sn-triageIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 50 | Claude Code |
| sn-uibIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 57 | Claude Code |
| sn-securityIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 73 | Claude Code |
| sn-upgradeIvanBBaev/servicenow-mcp-ai | Skill | 11 | 6d ago | GPL-3.0 | A | 62 | Claude Code |