Salesforce CLI

Safety-first wrapper for Salesforce CLI (sf v2). Every command is classified by risk level before execution. NEVER modify Salesforce data or metadata without explicit user permission.

When to Use

User asks to query Salesforce data (SOQL/SOSL)
User asks to deploy or retrieve metadata
User asks to export/import data (CSV, JSON, tree)
User asks to execute Apex code
User asks to manage orgs (scratch, sandbox, production)
User asks to authenticate w/ Salesforce
User asks to work w/ platform events or CDC
User asks to manage packages or permissions
User asks to interact w/ Salesforce APIs (REST, Bulk, Tooling)

Prerequisites

Install: npm install -g @salesforce/cli or brew install sf
Auth: sf org login web (interactive) or sf org login jwt (CI/CD)
Verify: sf --version (requires v2.x)
Default org: sf config set target-org <alias>

Safety Model

Every sf command falls into one of four risk tiers. Default mode is read-only.

Tier	Action Required	Examples
Safe	Execute immediately	`sf org list`, `sf data query`, `sf project retrieve preview`
Write	`AskUserQuestion` BEFORE executing	`sf data create record`, `sf project deploy start --dry-run`
Destructive	`AskUserQuestion` w/ explicit consequences	`sf project deploy start`, `sf data delete`, `sf org delete`
Forbidden	Multi-step validation, NEVER auto-confirm	Bulk delete in production, mass data wipe, production org delete

See references/safety-rules.md for full classification and confirmation templates.

Production Guardrails

Detect org type before ANY write operation:

sf org display --target-org <alias> --json

Check instanceUrl and isScratch/isSandbox fields:

login.salesforce.com or no sandbox/scratch flag → PRODUCTION → extra confirmation required
test.salesforce.com or isSandbox: true → Sandbox
isScratch: true → Scratch org

For production orgs: ALL write operations require AskUserQuestion w/ org alias typed confirmation.

Fail-Safe Principles

If org type detection fails → BLOCK all operations (never assume non-production)
If unsure about tier → classify HIGHER (Write → Destructive, Destructive → Forbidden)
Bulk operations always require row count preview before confirmation
Deploys with destructiveChanges.xml are FORBIDDEN in production via scripts
--test-level NoTestRun is BLOCKED for production deployments
Apex code must be shown to user BEFORE execution (never run sight-unseen)
Permission set changes require warning about privilege escalation / lockout risks
Field/object deletions in deploys require warning about cascade impacts (reports, flows, integrations)
Sandbox refresh requires explicit acknowledgment that ALL data will be overwritten
PII fields in queries trigger a warning (Email, Phone, Birthdate, SSN, etc.)

Decision Flow

Command received
  → Detect target org type (prod/sandbox/scratch)
  → Classify risk tier (see Quick Reference)
  → Safe?        Execute immediately
  → Write?       AskUserQuestion → wait for answer → execute or cancel
  → Destructive? AskUserQuestion w/ consequences → wait → execute or cancel
  → Forbidden?   Warn → require typed confirmation → final confirm → execute or cancel
  → PRODUCTION?  Add extra confirmation step regardless of tier

Quick Reference

Safe (read-only, execute immediately)

Command	Description
`sf org list`	List authorized orgs
`sf org list --all`	Include expired scratch orgs
`sf org display`	Display org info
`sf org open`	Open org in browser
`sf config list`	List config values
`sf config get target-org`	Get default org
`sf alias list`	List aliases
`sf data query --query "..."`	SOQL query (w/ mandatory LIMIT)
`sf data search --query "..."`	SOSL search
`sf data get record`	Get single record
`sf project retrieve preview`	Preview what would be retrieved
`sf project deploy preview`	Preview what would be deployed
`sf apex list log`	List debug logs
`sf apex get log`	Get debug log content
`sf apex tail log`	Tail logs in real-time
`sf api request rest` (GET)	Read-only REST API calls
`sf limits api display`	Display API limits
`sf schema generate sobject`	Describe object schema
`sf package list`	List packages
`sf package version list`	List package versions
`sf plugins list`	List installed plugins
`sf doctor`	Run diagnostics
`sf auth list`	List auth connections

Write (AskUserQuestion required)

Command	Description
`sf data create record`	Create a single record
`sf data update record`	Update a single record
`sf data import tree`	Import data from tree files
`sf project deploy start --dry-run`	Validate deployment (no changes)
`sf project retrieve start`	Retrieve metadata to local
`sf org create scratch`	Create scratch org
`sf alias set`	Set an alias
`sf config set`	Set config value
`sf package create`	Create a package
`sf package version create`	Create package version

Destructive (AskUserQuestion w/ consequences)

Command	Description
`sf project deploy start` (no dry-run)	Deploy metadata (modifies org)
`sf data delete record`	Delete a single record
`sf data delete bulk`	Bulk delete records
`sf data update bulk`	Bulk update records — can corrupt data at scale
`sf data import bulk`	Bulk import — can create thousands of duplicate records
`sf data upsert bulk`	Bulk upsert — incorrect key can overwrite wrong records
`sf apex run`	Execute anonymous Apex
`sf org delete scratch`	Delete scratch org
`sf org delete sandbox`	Delete sandbox
`sf org create sandbox`	Create sandbox (long-running, uses resources)
`sf org assign permset`	Assign permission set — can escalate privileges or lock users out
`sf package install`	Install package — can modify schema, automation, and data
`sf package uninstall`	Uninstall package
`sf org logout`	Remove org auth
`sf api request rest -X POST/PUT/PATCH/DELETE`	Write/delete REST API calls

Forbidden (multi-step validation)

Command	Description
`sf org delete` targeting production	Delete production org connection
Bulk delete in production	Mass data deletion in production
`sf data delete bulk` w/o WHERE in source query	Full-table data wipe risk
`sf project deploy start` w/ `destructiveChanges.xml` in prod	Deploy destructive metadata changes to production
`sf project deploy start --test-level NoTestRun` in prod	Skip tests in production (BLOCKED)
`sf org refresh sandbox`	Refresh sandbox — overwrites ALL data and customizations
`sf org logout --all`	Remove ALL org auth — can break CI/CD pipelines
Bulk loops w/o limits	Any loop running delete/update w/o LIMIT
`sf apex run` in production w/o review	Execute unreviewed Apex in production
Dangerous deploy flags in prod	`--ignore-conflicts`, `--ignore-warnings`, `--purge-on-delete`

SOQL/SOSL Query Safety

Mandatory rules for ALL queries:

Always add LIMIT — Default to LIMIT 200 if user omits
Never use SELECT * — Expand fields via sf schema generate sobject or ask user
Production queries — Require WHERE clause unless object is known to be small
Tooling API queries — Use --use-tooling-api flag for metadata queries

# Safe SOQL query
sf data quer

claude-skills-vault

How to add

Drop this on your repo README

Related skills

webapp-testing

brand-guidelines

frontend-design

mcp-builder

Get new Design e Frontend skills every Monday