workspace-builder

workspace-builder is a skill for Claude Code from serac-labs/serac. It costs 62 tokens per session (6,244 once invoked), scanned A, original, Apache-2.0.

A ServiceNow App Engine Studio guide for creating scoped applications, custom tables, workspaces, UI Builder experiences, data brokers, and export-ready application structures. App Engine Studio is ServiceNow's low-code application builder.

In plain words
What is it for?
Use it to create application scopes and tables, configure workspace lists and forms, connect UI Builder records, set up data access, and check export readiness.
Why use it?
It reduces errors caused by using the wrong ServiceNow records to represent applications, workspaces, pages, and routes.

Skill for Claude Code

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

Part of the servicenow plugin — 70 skills shipped together

Good fit Use it to create application scopes and tables, configure workspace lists and forms, connect UI Builder records, set up data access, and check export readiness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/serac-labs/serac/workspace-builder
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 serac-labs/serac --skill workspace-builder
Clone the repo
git clone --depth 1 https://github.com/serac-labs/serac

Made for: Claude Code.

Or install servicenow, the plugin that ships this one along with the rest of its 70 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 workspace-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/serac-labs/serac/workspace-builder/github.svg)](https://agentmods.dev/skills/serac-labs/serac/workspace-builder)
Your own site
<a href="https://agentmods.dev/skills/serac-labs/serac/workspace-builder"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/workspace-builder/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 workspace-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/serac-labs/serac/workspace-builder"><img src="https://agentmods.dev/badge/skills/serac-labs/serac/workspace-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,244 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 $0.00062 $0.06244
Opus 5.5 $0.00025 $0.02498
Sonnet 5.5 $0.00012 $0.01249
Haiku 4.5 $0.00006 $0.00624

Measured 1mo ago against content hash 30b9586ff149, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workspace-builder 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.

packages/skills/workspace-builder/SKILL.md · 548 lines

How it starts

The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Engine Studio & Workspace Builder for ServiceNow

App Engine Studio (AES) enables low-code application development with custom workspaces.

AES Architecture

Application (sys_scope)
    ├── Tables & Forms
    ├── Workflows
    ├── Workspaces (sys_aw_workspace)
    │   ├── Lists
    │   ├── Forms
    │   └── Dashboards
    └── Portals

Key Tables

Table Purpose
sys_scope Application scope
sys_app Application record
sys_aw_workspace Agent Workspace definition
sys_ux_experience Next Experience workspace — top of the UI Builder chain
sys_ux_app_config Workspace settings; links to the experience
sys_ux_macroponent Page content and custom components
sys_ux_page_registry Registers a macroponent as a page of an app config
sys_ux_app_route URL slug that reaches a registered page
sys_ux_page UI Builder page rows — read them, never insert one directly

Application Development (ES5)

Create Scoped Application

// Create scoped application (ES5 ONLY!)
var app = new GlideRecord("sys_scope")
app.initialize()

// Basic info
app.setValue("name", "IT Asset Tracker")
app.setValue("scope", "x_myco_asset_track")
app.setValue("short_description", "Track IT assets across the organization")
app.setValue("version", "1.0.0")

// Vendor
app.setValue("vendor", "My Company")
app.setValue("vendor_prefix", "x_myco")

// License
app.setValue("licensable", true)

app.insert()

Create Application Table

// Create table in scoped app (ES5 ONLY!)
function createAppTable(scope, tableDef) {
  var table = new GlideRecord("sys_db_object")
  table.initialize()

  table.setValue("name", scope + "_" + tableDef.name)
  table.setValue("label", tableDef.label)
  table.setValue("super_class", tableDef.extends || "task")

  // Scope assignment
  table.setValue("sys_scope", getAppSysId(scope))

  // Options
  table.setValue("is_extendable", tableDef.extendable || false)
  table.setValue("create_access_controls", true)

  table.insert()

  // Create fields
  if (tableDef.fields) {
    for (var i = 0; i < tableDef.fields.length; i++) {
      createField(scope + "_" + tableDef.name, tableDef.fields[i])
    }
  }

  return table.getUniqueValue()
}

// Example
createAppTable("x_myco_asset_track", {
  name: "asset_item",
  label: "Asset Item",
  extends: "cmdb_ci",
  fields: [
    { name: "u_purchase_date", label: "Purchase Date", type: "glide_date" },
    { name: "u_warranty_end", label: "Warranty End", type: "glide_date" },
    { name: "u_assigned_user", label: "Assigned User", type: "reference", reference: "sys_user" },
  ],
})

Read the full file on GitHub · 548 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. 1mo ago First seen · 548 lines · 62 tokens per session scan A 30b9586ff149

Subscribe to this mod's changes

workspace-builder is a skill published in the GitHub repository serac-labs/serac (78 stars, last pushed 6d ago), licensed Apache-2.0. It adds 62 tokens to every session and 6,244 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

sn-safe-write

Change ServiceNow data safely — plan first, apply only after review, verify, and know how to revert. Use whenever a create, update, upsert or delete on an instance is requested.

IvanBBaev/servicenow-mcp-ai · 43 tokens

sn-discover

Map a ServiceNow instance into Markdown (version and counts, custom applications, per-scope tables and artefacts) with the server's own document generator. Use when asked to discover, survey, inventory or document an instance or its custom apps.

IvanBBaev/servicenow-mcp-ai · 53 tokens

sn-triage

Triage a ServiceNow incident or a failing behaviour — instance health, recent errors, what automation runs on the table, and what changed on the record. Use when something is broken, slow or erroring on an instance.

IvanBBaev/servicenow-mcp-ai · 50 tokens

sn-uib

Review a ServiceNow UI Builder (UIB) experience or workspace page — its page map, what a change would touch, data broker security and page weight. Use when asked to explain, audit or assess a UI Builder page, workspace or experience before changing it.

IvanBBaev/servicenow-mcp-ai · 57 tokens

sn-security

Review the security posture of a ServiceNow instance — the ACL scan, hardening properties and cross-scope access — or explain why one user can or cannot read, write, create or delete a table, record or field. Use for a security review, a hardening check, or a "why can't this user see / edit it" question.

IvanBBaev/servicenow-mcp-ai · 73 tokens

sn-upgrade

Review ServiceNow upgrade readiness — the upgrade history, the skipped records an upgrade left unresolved, base vs customer versions of one skip, and store apps with an update. Use after a family or patch upgrade, before planning one, or when asked which skipped records to revert, keep or merge.

IvanBBaev/servicenow-mcp-ai · 62 tokens