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.
/plugin marketplace add forcedotcom/sf-skillsnpx agentmods add plugins/forcedotcom/sf-skills/salesforce-test-drivegit 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-test-drive)<a href="https://agentmods.dev/plugins/forcedotcom/sf-skills/salesforce-test-drive"><img src="https://agentmods.dev/badge/plugins/forcedotcom/sf-skills/salesforce-test-drive.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
salesforce-test-drive 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.
What it actually says
{
"name": "salesforce-test-drive",
"displayName": "Salesforce Test Drive",
"version": "0.1.0",
"description": "Take a Salesforce capability for a test drive — pick a curated end-to-end build from a menu (e.g. a Service help agent delivered as a website chat widget) and watch it run start to finish. A guided, rehearsable demo and learning engine that checks readiness, helps you connect or provision an org, then choreographs the salesforce-development skills to build the real thing.",
"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-test-drive",
"repository": "https://github.com/forcedotcom/sf-skills.git",
"keywords": [
"salesforce",
"test-drive",
"demo",
"agentforce",
"service-cloud",
"onboarding",
"guided-build"
],
"dependencies": ["salesforce-development"],
"commands": "./commands/"
}
What it installs
The manifest is a name and a version. 1 command travel with it, and installing the plugin installs all of them — 64 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today First seen · 22 lines scan A 9ddbf073aa93
salesforce-test-drive 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.
Other plugins, from other repositories
Master-skill
FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready. 15 prebuilt masters across 印度/汉传/藏传/南传 plus compare, debate, and curriculum meta-skills.
ida-plugin-development
Skills, knowledge, and scripts for developing plugins for IDA Pro in Python, using idiomatic patterns, lessons, and tricks.
unslop
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…
yggdrasil
One shared, durable memory for your AI coding agents — local-first, zero-dependency. Decisions, lessons and status persist across sessions, tools and projects.
observer
Turn a video or podcast into a study session: transcript, prepared concepts, and charts the agent builds and verifies. Pause anywhere and ask; the agent knows the second you are on. Ships the observer skill and its MCP server.
language-coach
Real-time language coaching in Claude Code. Set your native and target language, get corrections and natural expressions on every prompt.