salesforce-development

salesforce-development is a plugin for Claude Code from forcedotcom/sf-skills. Its manifest loads nothing; the 37 skills, 13 commands, 2 agents, 3 MCP servers it bundles cost 5,939 tokens per session together, scanned A, original, Apache-2.0.

A general toolkit for building Salesforce applications and agents, covering configuration, Apex code, data queries, deployment, security, and reports.

In plain words
What is it for?
It is for creating and changing Salesforce metadata, writing Apex and queries, deploying or retrieving project files, and working with Salesforce security and reporting.
Why use it?
It brings common Salesforce development work into one coding-agent add-on instead of requiring separate guidance for each area.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add forcedotcom/sf-skills
agentmods
npx agentmods add plugins/forcedotcom/sf-skills/salesforce-development
Clone the repo
git clone --depth 1 https://github.com/forcedotcom/sf-skills

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-development

README.md
[![agentmods](https://agentmods.dev/badge/plugins/forcedotcom/sf-skills/salesforce-development.svg)](https://agentmods.dev/plugins/forcedotcom/sf-skills/salesforce-development)
Your own site
<a href="https://agentmods.dev/plugins/forcedotcom/sf-skills/salesforce-development"><img src="https://agentmods.dev/badge/plugins/forcedotcom/sf-skills/salesforce-development.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 37 skills, 13 commands, 2 agents, 3 MCP servers cost 5,939 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

salesforce-development 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 today.

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.

plugins/builder/salesforce-development/.claude-plugin/plugin.json · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "salesforce-development",
  "displayName": "Salesforce Development",
  "version": "2.1.0",
  "description": "Build Salesforce apps and agents using these core building blocks: metadata, Apex, deploy/retrieve, security, reporting, and generated installed-versus-available capability discovery.",
  "author": { "name": "Salesforce", "url": "https://github.com/forcedotcom/sf-skills" },
  "license": "Apache-2.0",
  "homepage": "https://github.com/forcedotcom/sf-skills/tree/main/plugins/builder/salesforce-development",
  "repository": "https://github.com/forcedotcom/sf-skills.git",
  "keywords": ["salesforce", "apex", "flow", "soql", "metadata", "deploy"],
  "dependencies": [],
  "userConfig": {
    "ui_mode": {
      "type": "string",
      "title": "Salesforce development UI mode",
      "description": "Ambient UI: full (default), compact, plain semantic text, or off. Explicit commands and safety guidance remain available.",
      "default": "full"
    },
    "plugin_match_sensitivity": {
      "type": "string",
      "title": "Uninstalled-plugin recommendation sensitivity",
      "description": "How readily this plugin proposes an uninstalled Salesforce plugin matching your task: off (never), low, standard (default), high, or a custom number from 1.0-10.0. Change it any time from within a session with /salesforce-development:plugin-recommendations.",
      "default": "standard"
    }
  },
  "skills": "./skills/",
  "commands": "./commands/",
  "hooks": {
    "SessionStart": [
      {
        "matcher": "*",
        "hooks": [
          {
            "type": "command",
            "command": "\"${CLAUDE_PLUGIN_ROOT}\"/scripts/sf-context detect",
            "statusMessage": "Loading local Salesforce project context…"
          },
          {
            "type": "command",
            "command": "\"${CLAUDE_PLUGIN_ROOT}\"/scripts/sf-context telemetry-capture session_start"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bas

Read the full file on GitHub · 281 lines

Contents

What it installs

The manifest is a name and a version. 37 skills, 13 commands, 2 agents, 3 MCP servers travel with it, and installing the plugin installs all of them — 5,939 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. today First seen · 281 lines scan A c21c79de64aa

Subscribe to this mod's changes

salesforce-development is a plugin published in the GitHub repository forcedotcom/sf-skills (961 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.