cli-command-development

Guidance for adding commands and command groups to a Salesforce B2C Commerce command-line program using oclif, a framework for building command-line tools. It covers command structure, options, arguments, output tables, and shared command classes.

In plain words
What is it for?
Use it when creating commands or topics, adding flags and arguments, producing table output, or connecting commands to authentication and Salesforce Commerce APIs.
Why use it?
It gives developers the project conventions and the right base class for each command, reducing mistakes when extending the CLI.

Skill for Claude CodeCodex

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 skills/salesforcecommercecloud/b2c-developer-tooling/cli-command-development
Any agent
npx skills add SalesforceCommerceCloud/b2c-developer-tooling --skill cli-command-development
Clone the repo
git clone --depth 1 https://github.com/SalesforceCommerceCloud/b2c-developer-tooling

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,501 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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.02501
Opus 5 $0.00026 $0.01251
Sonnet 5 $0.00010 $0.00500
Haiku 4.5 $0.00005 $0.00250

Measured 2d ago against content hash 8aa3ccc50bf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-command-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 2d 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.

.claude/skills/cli-command-development/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Command Development

This skill covers creating new CLI commands and topics for the B2C CLI.

Command Organization

Commands live in packages/b2c-cli/src/commands/. The directory structure maps directly to command names:

commands/
├── code/
│   ├── deploy.ts      → b2c code deploy
│   ├── activate.ts    → b2c code activate
│   └── list.ts        → b2c code list
├── sandbox/
│   ├── create.ts      → b2c sandbox create
│   └── list.ts        → b2c sandbox list
└── mrt/
    └── env/
        └── var/
            └── set.ts → b2c mrt env var set

Command Class Hierarchy

Choose the appropriate base class based on what your command needs:

BaseCommand (logging, JSON output, error handling)
  └─ OAuthCommand (OAuth authentication)
       ├─ InstanceCommand (B2C instance: hostname, code version)
       │   ├─ CartridgeCommand (cartridge path + filters)
       │   ├─ JobCommand (job execution helpers)
       │   └─ WebDavCommand (WebDAV root directory)
       ├─ MrtCommand (Managed Runtime API)
       └─ OdsCommand (On-Demand Sandbox API)

Import from @salesforce/b2c-tooling-sdk/cli:

import { InstanceCommand, CartridgeCommand, OdsCommand } from '@salesforce/b2c-tooling-sdk/cli';

Standard Command Template

/*
 * Copyright (c) 2025, Salesforce, Inc.
 * SPDX-License-Identifier: Apache-2
 * For full license text, see the license.txt file in the repo root
 */
import {Args, Flags} from '@oclif/core';
import {InstanceCommand} from '@salesforce/b2c-tooling-sdk/cli';
import {getApiErrorMessage} from '@salesforce/b2c-tooling-sdk';
import {t} from '../../i18n/index.js';

interface MyCommandResponse {
  success: boolean;
  data: SomeType[];
}

export default class MyCommand extends InstanceCommand<typeof MyCommand> {
  static description = t('commands.topic.mycommand.description', 'Human-readable description');

  static enableJsonFlag = true;

  static examples = [
    '<%= config.bin %> <%= command.id %> arg1',
    '<%= config.bin %> <%= command.id %> --flag value',
    '<%= config.bin %> <%= command.id %> --json',
  ];

  static args = {
    name: Args.string({
      description: 'Description of the argument',
      required: true,
    }),
  };

  static flags = {
    myFlag: Flags.string({
      char: 'm',
      description: 'Flag description',
      default: 'defaultValue',
    }),
    myBool: Flags.boolean({
      description: 'Boolean flag',
      default: false,
    }),
  };

  async run(): Promise<MyCommandResponse> {
    // Validation - call appropriate require* methods
    this.requireServer();

    // Access parsed args and flags
    const {name} = this.args;
    const {myFlag, myBool} = this.flags;

    this.log(t('commands.topic.mycommand.working', 'Working on {{name}}...', {name}));

    // Implementation
    const {data, error, response} = await this.instance.ocapi.GET('/some/endpoint');

    if (error) {
      this.error(t('commands.topic.mycommand.error', 'Failed: {{message}}', {
        message: getApiErrorMessage(error, response),
      }));
    }

    const result: MyCommandResponse = {
      success: true,
      data,
    };

    // JSON mode returns the object directly (oclif handles serialization)
    if (this.jsonEnabled()) {
      return result;
    }

    // Human-readable output
    this.log('Success!');
    return result;
  }
}

Read the full file on GitHub · 348 lines

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.

  1. 2d ago First seen · 348 lines · 52 tokens per session scan A 8aa3ccc50bf1

Subscribe to this mod's changes

cli-command-development is a skill published in the GitHub repository SalesforceCommerceCloud/b2c-developer-tooling (53 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,501 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 2026-08-30.

Related

Other skills, from other repositories

ios-simulator-skill

29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.

conorluddy/ios-simulator-skill · 47 tokens

mall4j

Mall4j 开源版现有功能副驾驶:本地启动、mall4v/mall4m/mall4uni、商品/SKU、购物车、下单支付、订单发货、会员、运费、权限、部署排查。适用于下载 mall4j / yami-shop 后按现有功能使用或二次开发;不要编造开源版没有的能力。.

gz-yami/mall4j · 89 tokens

Troubleshooting Guide Builder

Builds a structured troubleshooting guide with symptom → cause → fix format for any tool or system.

Notysoty/openagentskills · 25 tokens

Documentation Gap Finder

Audits a codebase or docs folder and lists everything that is undocumented, outdated, or unclear.

Notysoty/openagentskills · 24 tokens

agent-tail

Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.

gillkyle/agent-tail · 44 tokens

developer-experience

Developer Experience (DX) Audit: Assesses and improves developer productivity and satisfaction — build times, CI/CD speed, onboarding friction, tooling quality, documentation, and internal developer portal. Covers developer surveys, golden paths, platform engineering, and DX metrics. Use when the user mentions…

camilooscargbaptista/cto-toolkit · 97 tokens