forcedotcom/sf-skills is a collection of reusable instructions that help AI coding agents build and work with Salesforce applications and platform features. Developers use it for Agentforce agents, Lightning apps, Flow, Apex, SOQL, Lightning Web Components, and related Salesforce configuration. The catalogue entries are the repository’s skills, plugins, commands, MCP servers, and agents for AI tools that support skills.
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.
git clone --depth 1 https://github.com/forcedotcom/sf-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/plugins/forcedotcom/sf-skills/salesforce-development)<a href="https://agentmods.dev/plugins/forcedotcom/sf-skills/salesforce-development"><img src="https://agentmods.dev/badge/plugins/forcedotcom/sf-skills/salesforce-development/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/plugins/forcedotcom/sf-skills/salesforce-development"><img src="https://agentmods.dev/badge/plugins/forcedotcom/sf-skills/salesforce-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 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.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "salesforce-development",
"displayName": "Salesforce Development",
"version": "2.5.0",
"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": "Presentation mode",
"description": "Ambient UI, including answers to natural-language status, orientation, and capability questions: full (default) signature banner and graded nudge, plain accessible semantic text (no color or glyphs) for status and orientation, or off (silent for all three). Slash commands and safety guidance remain available in every mode.",
"options": ["full", "plain", "off"],
"default": "full"
},
"plugin_match_sensitivity": {
"type": "string",
"title": "Plugin recommendation",
"description": "How readily this plugin proposes an uninstalled Salesforce plugin matching your task: off (never), low, standard (default), or high. For a custom numeric threshold (1.0-10.0), set it from within a session with /salesforce-development:plugin-recommendations.",
"options": ["off", "low", "standard", "high"],
"default": "standard"
}
},
"skills": "./skills/",
"commands": "./commands/",
"hooks": {
"SessionStart": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PLUGIN_ROOT}\"/scripts/sf-context detect",
"statusMessage": "Loading local Salesforce prWhat it installs
The manifest is a name and a version. 37 skills, 14 commands, 1 agent, 3 MCP servers travel with it, and installing the plugin installs all of them — 4,579 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill platform-apex-generate A 122 tokens
- Skill platform-custom-field-generate A 139 tokens
- Skill platform-custom-metadata-type-generate A 136 tokens
- Skill platform-custom-setting-generate A 149 tokens
- Skill platform-data-and-tooling-api-context-get A 159 tokens
- Skill platform-metadata-api-context-get A 126 tokens
- Skill automation-flow-generate A 106 tokens
- Skill dx-org-manage A 127 tokens
- Skill platform-flexipage-generate A 112 tokens
- Skill platform-lightning-app-coordinate A 79 tokens
- Skill platform-sharing-rules-generate A 108 tokens
- Skill platform-value-set-generate A 111 tokens
- Skill platform-apex-anonymous-run A 119 tokens
- Skill platform-custom-object-generate A 108 tokens
- Skill platform-custom-report-type-generate A 99 tokens
- Skill platform-lsp-integrate A 125 tokens
- Skill platform-manifest-generate A 116 tokens
- Skill platform-apex-test-generate A 116 tokens
- Skill platform-data-manage A 115 tokens
- Skill platform-environment-validate A 104 tokens
- Skill platform-metadata-deploy A 110 tokens
- Skill platform-apex-logs-debug A 89 tokens
- Skill platform-apex-test-run A 92 tokens
- Skill platform-capability-search A 99 tokens
- Skill platform-custom-tab-generate A 86 tokens
- Skill platform-list-view-generate A 97 tokens
- Skill platform-permission-set-generate A 62 tokens
- Skill platform-report-generate A 115 tokens
- Skill platform-quick-deploy A 117 tokens
- Skill platform-soql-query A 112 tokens
- Skill platform-deploy-validate A 106 tokens
- Skill platform-custom-application-generate A 93 tokens
- Skill platform-sharing-owd-configure A 116 tokens
- Skill platform-metadata-retrieve A 120 tokens
- Skill platform-validation-rule-generate A 81 tokens
- Skill dx-project-create C 175 tokens
- Skill platform-destructive-deploy C 102 tokens
- Command feedback A 23 tokens
- Command reset-source-tracking A 43 tokens
- Command setup A 47 tokens
- Command login A 26 tokens
- Command plugin-recommendations A 20 tokens
- Command set-default A 34 tokens
- Command logout A 20 tokens
- Command telemetry A 24 tokens
- Command discover A 31 tokens
- Command plugin-install A 18 tokens
- Command org A 20 tokens
- Command project A 30 tokens
- Command status A 22 tokens
- Command welcome A 33 tokens
- Agent salesforce-dev A 40 tokens
- MCP server salesforce-api-context A not measured
- MCP server salesforce-metadata-experts A not measured
- MCP server salesforce-lsp A not measured
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.
- 4d ago Changed 94a109276817
- 11d ago Changed 98fd196cc008
- 18d ago Changed 2e4de5ab1ece
- 28d ago Changed · +17 lines a0db44fee3a1
- 1mo ago Changed · +14 lines 5e17515aa478
- 1mo ago First seen · 281 lines scan A c21c79de64aa
salesforce-development is a plugin published in the GitHub repository forcedotcom/sf-skills (1,104 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.
Other plugins, from other repositories
app-builder
Development, customization, testing, and deployment skills for Adobe App Builder projects, including the Workfront UI-extension suite (skills/appbuilder-workfront).
load-tester
Load and stress testing for APIs and web services.
rabbitmqadmin
Skill for inspecting RabbitMQ instances using the rabbitmqadmin CLI (rabbitmqadmin-ng).
rails-consultant
A collection of skills for Rails development and consulting, with an emphasis on learning, communication, and client success.
jpm-payments-skills
Conversational agent skills that walk a merchant from J.P. Morgan Payments onboarding through a working API integration. Supports Checkout and Online Payments in the initial release. Generates language-specific OAuth modules (Node/TypeScript, Python, Java idiomatic; other languages via canonical algorithm).
auth
Auth skills for Claude Code — scaffold hand-rolled auth endpoints and audit auth code against security best practices.