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 BanibrataChatterjee/AwesomeSalesforceSkills --skill fsc-referral-managementgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote 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/banibratachatterjee/awesomesalesforceskills/fsc-referral-management)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/fsc-referral-management"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/fsc-referral-management/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/banibratachatterjee/awesomesalesforceskills/fsc-referral-management"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/fsc-referral-management.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 | $0.00113 | $0.03340 |
| Opus 5.5 | $0.00045 | $0.01336 |
| Sonnet 5.5 | $0.00023 | $0.00668 |
| Haiku 4.5 | $0.00011 | $0.00334 |
Grade A, and why
fsc-referral-management 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FSC Referral Management
Use this skill when configuring FSC Referral Management: defining referral types via ReferralRecordTypeMapping__mdt custom metadata, routing referrals through Lead Assignment Rules keyed on the Expressed Interest picklist, understanding Referrer Score behavior, and enabling partner referral visibility in Experience Cloud. It activates whenever a practitioner needs to wire together the Lead-based referral data model, the custom metadata registry, the picklist-driven routing logic, and downstream queues or partner portals.
Before Starting
Gather this context before working on anything in this domain:
- Confirm the org has Financial Services Cloud provisioned and Referral Management is enabled in FSC Settings (Setup > Financial Services Cloud Settings > Referral Management toggle).
- Identify all referral types the business requires. Each must map to both a Lead record type and a
ReferralRecordTypeMapping__mdtentry — both are required for routing to function. - Confirm whether external partners submit referrals via an Experience Cloud site. If so, Referrer Score visibility requires explicit layout or component configuration that is off by default.
- The most common wrong assumption: adding a new queue is sufficient for routing. It is not. The queue must be referenced in an active
ReferralRecordTypeMapping__mdtentry or routing silently ignores it with no error. - Do not treat Einstein Referral Scoring as an active feature to configure. It was announced for retirement; Intelligent Need-Based Referrals is the supported scoring capability.
Core Concepts
The Extended Lead Object
FSC Referral Management does not introduce a separate object. It extends the standard Lead object with 11 custom fields that carry referral-specific data:
ExpressedInterest__c— picklist; the primary routing key for Lead Assignment RulesReferredBy__c— lookup to User (internal referrer) or Contact (external partner referrer)ReferrerScore__c— integer 0–100 reflecting the referrer's historical conversion rateReferralType__c— controlled by the record type selected at creationReferralDate__c,ReferralStatus__c,ReferralChannel__c, and four additional contextual fields
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.
- 1mo ago First seen · 203 lines · 113 tokens per session scan A 4ff1da6ce25b
fsc-referral-management is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 3,340 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
client-onboarding-design
Use this skill when designing the FSC client onboarding process — mapping document collection touchpoints, approval steps, compliance checkpoint sequencing, and welcome journey handoffs. Trigger keywords: client onboarding design, onboarding workflow requirements, document collection flow, compliance checkpoint…
community-engagement-strategy
Design the engagement model for an Experience Cloud community: reputation levels, ideation, and content contribution strategy. Triggers: 'community engagement strategy', 'gamification Experience Cloud', 'reputation levels setup', 'ideation community portal', 'member recognition program'. NOT for blocking, flagging or…
close-management
Manage the month-end close process with task sequencing, dependencies, and status tracking. Use when planning the close calendar, tracking close progress, identifying blockers, or sequencing close activities by day.
weekly-update
OpenDesign's weekly metrics standup: this week's numbers, the one anomaly, and the single decision it forces. Built as a decision-grade data & finance deck for ops & growth team.
procurement-optimizer
Use when running an annual SaaS audit, doing category-level spend review, or rationalizing the supplier base — when the user needs a spend audit, spend categorization (UNSPSC-aligned with Pareto breakdown and industry profiles), purchasing-cycle analysis (bottleneck categories per Goldratt's Theory of Constraints), or…
closing-checklist
What's blocking close — maintain the closing checklist with status, critical path, and days to close. Self-updating: ingests new items from diligence findings and schedule builds, tracks status, surfaces what's blocking. Use when user says "closing checklist", "what's left to close", "checklist status", "add to the…