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 Clientell-Ai/salesforce-skills --skill sf-flowgit clone --depth 1 https://github.com/Clientell-Ai/salesforce-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/clientell-ai/salesforce-skills/sf-flow)<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-flow"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-flow/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/clientell-ai/salesforce-skills/sf-flow"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-flow.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 | $0.00088 | $0.01824 |
| Opus 5 | $0.00044 | $0.00912 |
| Sonnet 5 | $0.00018 | $0.00365 |
| Haiku 4.5 | $0.00009 | $0.00182 |
Grade A, and why
sf-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Generator & Process Builder Migrator
You are a Salesforce Flow specialist. Generate valid .flow-meta.xml files and migrate Process Builders to optimized Flows.
Flow Best Practices
Architecture Rules
- Maximum 3 record-triggered flows per object (before-save, after-save, before-delete)
- Use a Custom Permission bypass mechanism for all record-triggered flows
- Consolidate Process Builder logic — do NOT create 1:1 naive conversions
- Use subflows for reusable logic
- Use fault connectors on all DML and callout elements
Bypass Pattern
Every record-triggered flow should start with a Decision element checking:
<decisions>
<name>Check_Bypass</name>
<label>Check Bypass</label>
<defaultConnector>
<targetReference>Main_Logic</targetReference>
</defaultConnector>
<defaultConnectorLabel>Continue</defaultConnectorLabel>
<rules>
<name>Is_Bypassed</name>
<conditionLogic>or</conditionLogic>
<conditions>
<leftValueReference>$Permission.Bypass_Automation</leftValueReference>
<operator>EqualTo</operator>
<rightValue>
<booleanValue>true</booleanValue>
</rightValue>
</conditions>
<label>Bypassed</label>
</rules>
</decisions>
Flow Types
-
Record-Triggered Flow (replaces Process Builder + Workflow Rules)
before save— field updates (no DML needed, most efficient)after save— related record updates, callouts, platform eventsbefore delete— validation, cascade operations
-
Screen Flow — user-facing wizards, guided processes
-
Autolaunched Flow — invoked by Apex, other flows, or platform events
-
Scheduled Flow — time-based batch operations
Flow XML Structure
<?xml version="1.0" encoding="UTF-8"?>
<Flow xmlns="http://soap.sforce.com/2006/04/metadata">
<apiVersion>62.0</apiVersion>
<label>Account Before Save</label>
<processType>AutoLaunchedFlow</processType>
<triggerType>RecordBeforeSave</triggerType>
<objectType>Account</objectType>
<triggerOrder>1</triggerOrder>
<status>Active</status>
<!-- Elements go here -->
</Flow>
What ships with it
2 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.
- 11d ago First seen · 179 lines · 88 tokens per session scan A 696b7e7c708a
sf-flow is a skill published in the GitHub repository Clientell-Ai/salesforce-skills (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 1,824 once invoked, about $0.0004 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
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
backend-api
Builds server-side endpoints and data access: REST or GraphQL routes, input validation, auth flows, queries, and error contracts, contract-first and framework-agnostic. Use when adding an endpoint or API surface, wiring login, session, token, or permission logic, or writing server-side business logic that persists…
api-verification
An API verification workflow that creates both an .http request file and a .cjs JavaScript file, then runs an automation script to test them. An API is an interface through which software exchanges requests and responses.
api-contract-architecture
An architecture guide for public APIs, including HTTP services, software-development kits, command-line tools, schemas, types, errors, pagination, filtering, and compatibility.
backend-domain-architecture
A review guide for backend and business-domain design. It examines business rules, workflows, permissions, APIs, transactions, consistency, repeated requests, compatibility, data boundaries, and service responsibilities.
distributed-systems-architecture
An architecture guide for distributed systems—software split across services that communicate over networks.