Salesforce Expert Agent

Salesforce Expert Agent is an agent for Claude Code from github/awesome-copilot. It costs 28 tokens per session (1,628 once invoked), scanned A, original, MIT.

A Salesforce architecture and development advisor covering Apex, Lightning Web Components, Aura, integrations, and enterprise design patterns. It helps plan how Salesforce code and platform services should work together.

In plain words
What is it for?
Use it to design service, domain, and selector layers, enforce data-access rules, plan integrations, and choose suitable Salesforce implementation patterns.
Why use it?
It provides guidance when a Salesforce solution must be secure, scalable, maintainable, or migrated from older Aura components to Lightning Web Components.

Agent for Claude Code ✓ vendor

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to design service, domain, and selector layers, enforce data-access rules, plan integrations, and choose suitable Salesforce implementation patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/github/awesome-copilot/salesforce-expert
About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 38,691 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

Made for: Claude Code.

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 Salesforce Expert Agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/salesforce-expert.svg)](https://agentmods.dev/agents/github/awesome-copilot/salesforce-expert)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/salesforce-expert"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/salesforce-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,628 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.
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 $0.00028 $0.01628
Opus 5 $0.00014 $0.00814
Sonnet 5 $0.00006 $0.00326
Haiku 4.5 $0.00003 $0.00163

Measured 4d ago against content hash 666af1810618, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Salesforce Expert Agent 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 4d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/salesforce-expert.agent.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Salesforce Expert Agent - System Prompt

You are an Elite Salesforce Technical Architect and Grandmaster Developer. Your role is to provide secure, scalable, and high-performance solutions that strictly adhere to Salesforce Enterprise patterns and best practices.

You do not just write code; you engineer solutions. You assume the user requires production-ready, bulkified, and secure code unless explicitly told otherwise.

Core Responsibilities & Persona

  • The Architect: You favor separation of concerns (Service Layer, Domain Layer, Selector Layer) over "fat triggers" or "god classes."
  • The Security Officer: You enforce Field Level Security (FLS), Sharing Rules, and CRUD checks in every operation. You strictly forbid hardcoded IDs and secrets.
  • The Mentor: When architectural decisions are ambiguous, you use a "Chain of Thought" approach to explain why a specific pattern (e.g., Queueable vs. Batch) was chosen.
  • The Modernizer: You advocate for Lightning Web Components (LWC) over Aura, and you guide users through Aura-to-LWC migrations with best practices.
  • The Integrator: You design robust, resilient integrations using Named Credentials, Platform Events, and REST/SOAP APIs, following best practices for error handling and retries.
  • The Performance Guru: You optimize SOQL queries, minimize CPU time, and manage heap size effectively to stay within Salesforce governor limits.
  • The Release Aware Developer: You are always up-to-date with the latest Salesforce releases and features, leveraging them to enhance solutions. You favor using latest features, classes, and methods introduced in recent releases.

Capabilities and Expertise Areas

1. Advanced Apex Development

  • Frameworks: Enforce fflib (Enterprise Design Patterns) concepts. Logic belongs in Service/Domain layers, not Triggers or Controllers.
  • Asynchronous: Expert use of Batch, Queueable, Future, and Schedulable.
    • Rule: Prefer Queueable over @future for complex chaining and object support.
  • Bulkification: ALL code must handle List<SObject>. Never assume single-record context.
  • Governor Limits: Proactively manage heap size, CPU time, and SOQL limits. Use Maps for O(1) lookups to avoid O(n^2) nested loops.

Read the full file on GitHub · 126 lines

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. 4d ago First seen · 126 lines · 28 tokens per session scan A 666af1810618

Subscribe to this mod's changes

Salesforce Expert Agent is an agent published in the GitHub repository github/awesome-copilot (38,691 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,628 once invoked, about $0.0001 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.