A command that starts a guided Salesforce test drive against a connected organisation. It checks whether the environment is ready, presents available demonstrations, and runs the selected build.

Use it to start a selected test-drive scenario or open the menu of available Salesforce demonstrations.

It provides one entry point for launching a complete Salesforce capability test instead of assembling the setup and steps manually.

start — Command for coding agents by forcedotcom: A command that starts a guided Salesforce test drive…

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.

agentmods

npx agentmods add commands/forcedotcom/sf-skills/start

Clone the repo

git clone --depth 1 https://github.com/forcedotcom/sf-skills

Or install salesforce-test-drive, the plugin that ships this one along with the rest of its 1 command.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/forcedotcom/sf-skills/start.svg)](https://agentmods.dev/commands/forcedotcom/sf-skills/start)

Your own site

<a href="https://agentmods.dev/commands/forcedotcom/sf-skills/start"><img src="https://agentmods.dev/badge/commands/forcedotcom/sf-skills/start.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 481 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00064	$0.00481
Opus 5	$0.00032	$0.00241
Sonnet 5	$0.00013	$0.00096
Haiku 4.5	$0.00006	$0.00048

Measured today against content hash 9ea42d7a46a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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-test-drive/commands/start.md · 41 lines

What it actually says

You are launching the Test Drive engine through /salesforce-test-drive:start — this plugin's single command and entry point.

Parse $ARGUMENTS: an optional test-drive id to launch directly (skip the menu), and an optional --instrument flag. Then read the engine and follow it exactly, start to finish:

echo "PLUGIN_ROOT=${CLAUDE_PLUGIN_ROOT}"
cat "${CLAUDE_PLUGIN_ROOT}/references/engine.md"

PLUGIN_ROOT echoed above is this plugin's absolute path, already resolved by Claude Code here in the command. Remember that value and pass it to the engine as PLUGIN_ROOT. The engine reads its catalog, prompts, and instrumentation spec from <PLUGIN_ROOT>/…; substitute this absolute path wherever it does. Do not type the literal ${CLAUDE_PLUGIN_ROOT} into a Bash command — that token only resolves inside a command body like this one, not in the engine's text, and your Bash shell has no such variable (it would expand to an empty string and break the path).

If $ARGUMENTS named an id, run the engine with SELECTED_DRIVE set to that id (Step 3 skips the menu).
Otherwise run the engine with SELECTED_DRIVE empty — Step 3 presents the catalog menu and lets the user choose.
Pass the --instrument flag through to the engine's Step 5.

The engine owns all of the logic (companion check, toolchain preflight, org detection, tiered provisioning, requirements gate, launch, handoff). Do not reimplement any of it here.

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.

today First seen · 41 lines · 64 tokens per session scan A 9ea42d7a46a4

Subscribe to this mod's changes

start is a command published in the GitHub repository forcedotcom/sf-skills (961 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 481 once invoked, about $0.0003 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.

Learning and teaching Productivity

start

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

review

learn-story-flow

no-vibe

learn

OPSX: Onboard

debrief