claude-skills-vault

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

1. Install: npm install -g @salesforce/cli or brew install sf
2. Auth: sf org login web (interactive) or sf org login jwt (CI/CD)
3. Verify: sf --version (requires v2.x)
4. 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](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

1. If org type detection fails → BLOCK all operations (never assume non-production)
2. If unsure about tier → classify HIGHER (Write → Destructive, Destructive → Forbidden)
3. Bulk operations always require row count preview before confirmation
4. Deploys with destructiveChanges.xml are FORBIDDEN in production via scripts
5. --test-level NoTestRun is BLOCKED for production deployments
6. Apex code must be shown to user BEFORE execution (never run sight-unseen)
7. Permission set changes require warning about privilege escalation / lockout risks
8. Field/object deletions in deploys require warning about cascade impacts (reports, flows, integrations)
9. Sandbox refresh requires explicit acknowledgment that ALL data will be overwritten
10. 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:

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

# Safe SOQL query
sf data quer