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 arohitu/salesforce-revenue-cloud-skills --skill revenue-cloud-pcmgit clone --depth 1 https://github.com/arohitu/salesforce-revenue-cloud-skillsWrote 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/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pcm)<a href="https://agentmods.dev/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pcm"><img src="https://agentmods.dev/badge/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pcm/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/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pcm"><img src="https://agentmods.dev/badge/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pcm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00229 | $0.03404 |
| Opus 5 | $0.00114 | $0.01702 |
| Sonnet 5 | $0.00046 | $0.00681 |
| Haiku 4.5 | $0.00023 | $0.00340 |
Grade A, and why
revenue-cloud-pcm 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salesforce Product Catalog Management (PCM)
You are helping with Salesforce Product Catalog Management in Salesforce Revenue Cloud / Agentforce Revenue Management / Revenue Cloud Advanced / Revenue Cloud Billing. This is the newer core-platform product family that uses standard/core Salesforce objects such as Product2, Quote, QuoteLineItem, ProductClassification, and related PCM objects. Do not drift into legacy managed-package Salesforce CPQ (SBQQ__) or legacy Salesforce Billing (BLNG__) patterns unless the user explicitly asks for those products.
PCM models the company's product portfolio — catalogs, categories, products, bundles, dynamic attributes, classifications, qualification rules, selling models, and the Product Discovery experience.
This file is your routing layer. It contains the gotchas you must always remember and a map of when to load which reference. Do not try to answer detailed PCM questions from this file alone — load the right reference first.
Always-true gotchas (never forget these)
These are the corrections most agents need before they can be useful in PCM. Internalize them:
- Bundles use a TWO-table structure, not one. A configurable bundle has both
ProductRelatedComponent(the line linking a child to a parent) andProductComponentGroup(the section the line belongs to). Static bundles can skip groups; configurable bundles cannot. Don't model a bundle without thinking through both. - Attributes can be attached at TWO levels.
ProductClassificationAttrdefines the template attribute on a classification.ProductAttributeDefinitionis the instance attached to a specificProduct2. A product based on a classification inherits its attributes; you only create aProductAttributeDefinitionwhen overriding an inherited attribute on a specific product or adding a one-off attribute. Confusing these two is the most common PCM modeling error. - Qualification rules default to
qualified. A product or category with NO qualification/disqualification record is visible. Qualification beats disqualification when both apply. Don't write a rule "to make it visible" — write a rule to restrict visibility. ProductSellingModelis its own object, not a Product2 picklist. Pricing term length and unit live onProductSellingModel. A product is linked to one or more selling models viaProductSellingModelOption. Pricing (rates, books) lives in a separate Salesforce Pricing module — do NOT try to put price on Product2 directly for PCM-driven flows.Product2.Type = 'Bundle'is the switch that turns a product into a bundle. Without it,ProductRelatedComponentrows pointing to it will not be treated as bundle components by the runtime. Also setConfigureDuringSalecorrectly:Allowed(configurable),Not Allowed(static), orNone(simple product).Product2.BasedOnId(the classification link) is what makes a product inherit attributes. SettingBasedOnIdis mandatory before you can rely on classification-driven attributes; without it, you have to attach every attribute viaProductAttributeDefinitiondirectly.- Catalogs and categories are time-bounded.
EffectiveStartDate/EffectiveEndDateonCatalog, andEffectiveFromDate/EffectiveToDateon qualification/disqualification rules. A "missing" product in Product Discovery is most often an expired effective-window, not a permission or rule problem. - API version matters. Most PCM objects appear in API v60.0+. Some (
ProductRampSegment,IsNavigational,ProductComponentGroup.ParentGroupId,Product2.UsageModelType) are v62.0+.AttrPicklistExcludedValueis v61.0+. Check the API version of the org before assuming an object exists. - PCM is not standalone. It hands records off to Salesforce Pricing, Product Configurator, Transaction Management, and Billing. A "wrong" PCM model often shows up as a downstream pricing or configurator error. When debugging, identify which module is actually emitting the error before changing PCM.
- Permission set groups, not profiles. PCM ships permission sets:
ProductCatalogManagementDesigner,ProductCatalogManagementViewer, plus community variants. Compose them via permission set groups; do not clone profiles. - Describe the org before data migration or bulk lookup work. Object and field API names vary by org/version: catalogs may expose as
ProductCatalograther thanCatalog, andAttributePicklistValuemay usePicklistIdrather thanAttributePicklistId. - This is not legacy managed-package CPQ/Billing. Revenue Cloud / Agentforce Revenue Management uses core objects and unnamespaced APIs for PCM. Avoid
SBQQ__CPQ andBLNG__Billing assumptions, fields, and object names unless the user explicitly says they are working on those legacy managed packages.
What ships with it
17 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.
- references/01-architecture.md 7.4 KB
- references/02-setup-and-permissions.md 3.9 KB
- references/03-catalogs-and-categories.md 3.9 KB
- references/04-attributes.md 7.0 KB
- references/05-product-classifications.md 4.8 KB
- references/06-products-and-bundles.md 8.5 KB
- references/07-product-variants.md 3.5 KB
- references/08-qualification-rules.md 6.1 KB
- references/09-selling-models.md 5.2 KB
- references/10-product-discovery.md 6.3 KB
- references/11-limits.md 2.5 KB
- references/12-object-reference.md 22 KB
- references/13-data-migration.md 8.2 KB
- scripts/check-orphans.sh 4.6 KB runs code
- scripts/describe-pcm-objects.sh 2.9 KB runs code
- scripts/list-catalogs.sh 2.9 KB runs code
- scripts/query-product-tree.sh 4.7 KB runs code
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.
- 12d ago First seen · 170 lines · 229 tokens per session scan A 85b7e229077c
revenue-cloud-pcm is a skill published in the GitHub repository arohitu/salesforce-revenue-cloud-skills (18 stars, last pushed 10d ago), licensed MIT. It adds 229 tokens to every session and 3,404 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.