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-pricing-diagnosticsgit 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-pricing-diagnostics)<a href="https://agentmods.dev/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pricing-diagnostics"><img src="https://agentmods.dev/badge/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pricing-diagnostics/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-pricing-diagnostics"><img src="https://agentmods.dev/badge/skills/arohitu/salesforce-revenue-cloud-skills/revenue-cloud-pricing-diagnostics.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 | $0.00112 | $0.01552 |
| Opus 5.5 | $0.00045 | $0.00621 |
| Sonnet 5.5 | $0.00022 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
revenue-cloud-pricing-diagnostics 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revenue Cloud Pricing Diagnostics
Use this skill to analyze Salesforce Revenue Cloud pricing implementations on core Salesforce Revenue Cloud / Agentforce Revenue Management. This is not Salesforce CPQ / Steelbrick CPQ. Do not start from SBQQ__* objects, CPQ price rules, product rules, or quote calculator plugins unless the user is explicitly asking about Salesforce CPQ instead of Revenue Cloud.
Default Workflow
When the user asks how a pricing field is populated, why a price changed, or how pricing logic works:
- Identify the commercial object and field: Quote, Quote Line, Order, Order Item, Contract, Asset, or another mapped object. In an SFDX project, fields are usually under
force-app/main/default/objects/<ObjectApiName>/fields/<FieldApiName>.field-meta.xml. Inspect XML tags such as<fullName>,<type>,<formula>,<formulaTreatBlanksAs>,<precision>,<scale>, and<required>. - Read the field metadata. Determine whether it is stored, formula, standard, custom, read-only, or calculated elsewhere. If the field is a formula, trace the fields referenced in
<formula>before assuming pricing writes to it directly. - Find matching context attributes and context tags in context definitions. In SFDX source, these are usually under
force-app/main/default/contextDefinitions/*.contextDefinition-meta.xml. Inspect<contextNodes>,<contextAttributes>,<title>,<dataType>,<fieldType>,<transient>, and<contextTags><title>.... - Inspect context mappings for both hydration and persistence in the same context definition metadata. Look under
<contextMappings>,<contextMappingIntents><mappingIntent>,<contextNodeMappings>,<contextAttributeMappings>,<contextAttrHydrationDetails>,<objectName>,<queryAttribute>,<contextAttribute>,<contextInputAttributeName>,<contextNode>, and<object>. - Trace bidirectionally between sObject fields and pricing tags. If a pricing step writes to a tag such as
EffectiveFromorEffectiveTo, find the context attribute that owns that tag, confirm it isinputoutputor output-capable, then trace its persistence mapping back to the target sObject field. Do not conclude a field is read-only to pricing until the save/writeback mapping has been checked. - Search expression set versions for the context tag, variable, output parameter, assignment, formula, aggregation, list operation, matrix lookup, or stop-pricing step. In SFDX source, pricing procedures are usually under
force-app/main/default/expressionSetVersion/*.expressionSetVersion-meta.xml. Inspect<variables>,<name>,<input>,<output>,<dataType>,<steps>,<actionType>,<customElement>,<parameters>,<sequenceNumber>,<parentStep>, and<stepType>. - Inspect pricing elements and decision table references. Decision tables are usually under
force-app/main/default/decisionTables/*.decisionTable-meta.xml, with dataset links underforce-app/main/default/decisionTableDatasetLinks/*.decisionTableDatasetLink-meta.xml. Confirm<decisionTableParameters>,<fieldName>,<usage>,<operator>,<sequence>,<isRequired>, condition criteria, outputs, backing object/source, and active status. - Identify procedure-plan sequence when available. Procedure-plan deployable metadata may not exist in source; if absent, query the org for
ProcedurePlanDefinition,ProcedurePlanDefinitionVersion,ProcedurePlanSection, andProcedurePlanOption. Apex hooks referenced by procedure plans are usually underforce-app/main/default/classes/<ClassName>.cls. - Produce a lineage report with evidence, likely failure points, and focused next checks.
What ships with it
6 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.
- 2mo ago First seen · 76 lines · 112 tokens per session scan A f0874eda62c4
revenue-cloud-pricing-diagnostics is a skill published in the GitHub repository arohitu/salesforce-revenue-cloud-skills (21 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,552 once invoked, about $0.0004 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 2026-08-30.
revenue-cloud-pricing-diagnostics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| revenue-cloud-pricing-diagnosticsarohitu/salesforce-revenue-cloud-skills | Skill | 21 | 2mo ago | MIT | A | 112 | Claude Code, Codex |
| revenuecat-troubleshootRevenueCat/ai-toolkit | Skill | 79 | yesterday | MIT | A | 125 | Claude Code |
| b2c-logsSalesforceCommerceCloud/b2c-developer-tooling | Skill | 58 | today | Apache-2.0 | A | 100 | Claude Code |
| vendure-troubleshootingvendurehq/vendure | Skill | 8.6k | yesterday | none | A | 89 | Claude Code |
| doctorHainrixz/agente-pagokit | Skill | 69 | 13d ago | MIT | A | 105 | Claude Code |
| b2c-production-triageSalesforceCommerceCloud/b2c-developer-tooling | Skill | 58 | today | Apache-2.0 | A | 58 | Claude Code |
| sfcc-webdav-workflowstaurgis/sfcc-dev-mcp | Skill | 28 | 6d ago | MIT | A | 56 | Claude Code, Codex |