platform-custom-field-generate

platform-custom-field-generate is a skill for Claude Code from forcedotcom/sf-skills. It costs 194 tokens per session (6,041 once invoked), scanned A, original, Apache-2.0.

A generator and validator for Salesforce custom fields, including picklists, formulas, relationships, roll-up summaries, and master-detail fields.

In plain words
What is it for?
Creating or updating fields on Salesforce objects and producing valid field metadata.
Why use it?
It handles field types with strict metadata rules and checks their configuration before deployment.

Skill for Claude Code

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

Part of the salesforce-development plugin — 37 skills, 13 commands, 2 agents, 3 MCP servers shipped together

Good fit Creating or updating fields on Salesforce objects and producing valid field metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forcedotcom/sf-skills/platform-custom-field-generate
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 forcedotcom/sf-skills --skill platform-custom-field-generate
Clone the repo
git clone --depth 1 https://github.com/forcedotcom/sf-skills

Made for: Claude Code.

Or install salesforce-development, the plugin that ships this one along with the rest of its 37 skills, 13 commands, 2 agents, 3 MCP servers.

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 platform-custom-field-generate

README.md
[![agentmods](https://agentmods.dev/badge/skills/forcedotcom/sf-skills/platform-custom-field-generate/github.svg)](https://agentmods.dev/skills/forcedotcom/sf-skills/platform-custom-field-generate)
Your own site
<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/platform-custom-field-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/platform-custom-field-generate/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 platform-custom-field-generate

Your own site · 80×15
<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/platform-custom-field-generate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/platform-custom-field-generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,041 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. Third-party audits
  • Socket pass 28 Aug 2026
  • Snyk pass 28 Aug 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00194 $0.06041
Opus 5 $0.00097 $0.03021
Sonnet 5 $0.00039 $0.01208
Haiku 4.5 $0.00019 $0.00604

Measured 6d ago against content hash 5ac41d843bdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

platform-custom-field-generate 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 6d 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.

plugins/builder/salesforce-development/skills/platform-custom-field-generate/SKILL.md · 474 lines

How it starts

The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Salesforce Custom Field Generator and Validator

Overview

Generates and validates Salesforce CustomField metadata XML, with special handling for the highest-failure-rate types — Roll-Up Summary and Master-Detail. The agent must verify the constraints below before outputting XML to prevent Metadata API deployment errors.


1. Universal Mandatory Attributes

Every generated field must include these tags:

Attribute Requirement Notes
<fullName> Required Field name only: derive from <label> — capitalize each word, replace spaces with _, append __c. Must start with a letter. E.g., label Total Contract ValueTotal_Contract_Value__c. This rule is for the FIELD name. Picklist VALUE <fullName> is different — keep it exactly as the user spelled it, spaces and all, no __c (e.g. Closed Won, NOT Closed_Won). See references/advanced-picklists.md (ref §3).
<label> Required The UI name (Title Case)
<description> Always include Explain the business reason why this field exists.
<inlineHelpText> Always include Actionable end-user guidance that adds value beyond the label (e.g., "Enter the value in USD including tax", not "The amount").

<description> and <inlineHelpText> are mandatory even though the Metadata API does not enforce them — omitting them yields low-quality metadata.

File path (SFDX source format): save each field as force-app/main/default/objects/<Object>/fields/<FieldName>__c.field-meta.xml, where <Object> is the object's API name (Account, Opportunity, or a custom Inventory_Item__c). A correct XML at the wrong path is never seen by the Metadata API.

External ID Configuration

Trigger: If the user mentions "integration," "importing data," "external system ID," or "unique key from [System Name]," set <externalId>true</externalId>.

Applicable Types: Text, Number, Email


Read the full file on GitHub · 474 lines

Files

What ships with it

1 file 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.

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. 6d ago First seen · 474 lines · 194 tokens per session scan A 5ac41d843bdf

Subscribe to this mod's changes

platform-custom-field-generate is a skill published in the GitHub repository forcedotcom/sf-skills (978 stars, last pushed yesterday), licensed Apache-2.0. It adds 194 tokens to every session and 6,041 once invoked, about $0.0010 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

fcakyon/claude-codex-settings · 22 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens

openloomi-api

OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…

melandlabs/openloomi · 106 tokens

nw-ddd-eventsourcing

Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.

nWave-ai/nWave · 38 tokens